Japanese models
Models built with Japanese use in mind, split into three groups by facts (sorted by downloads). This is not a rating or ranking of Japanese ability.
Models from Japanese developers
The original model is published by a Japanese company or research institute (llm-jp, ELYZA, SB Intuitions, CyberAgent, rinna, Preferred Networks and others).
-
33.2B
llm-jp
llm-jp-4-33b-thinking
- Q4_K_M size
- 20.2 GB
- Memory at 8K
- 23.3 GB
Measured Estimated VRAM 24 GB+
-
0.9B
pfnet
plamo-3-translate-0.8b
- Q4_K_M size
- 0.57 GB
- Memory at 8K
- 1.36 GB
Measured Estimated VRAM 4 GB+
-
2.9B
pfnet
plamo-3-translate-2b
- Q4_K_M size
- 1.81 GB
- Memory at 8K
- 2.72 GB
Measured Estimated VRAM 4 GB+
-
8.5B
pfnet
plamo-3-translate-8b
- Q4_K_M size
- 5.28 GB
- Memory at 8K
- 6.25 GB
Measured Estimated VRAM 6 GB+
-
32.1B
llm-jp
llm-jp-4.1-32b-a3b-thinking
- Q4_K_M size
- 21.5 GB
- Memory at 8K
- 23.1 GB
Measured Estimated VRAM 24 GB+
-
31.8B
pfnet
plamo-3-translate-31b
- Q4_K_M size
- 19.5 GB
- Memory at 8K
- 21.1 GB
Measured Estimated VRAM 24 GB+
-
8B
tokyotech-llm
Llama-3.1-Swallow-8B-Instruct-v0.5
- Q4_K_M size
- 4.92 GB
- Memory at 8K
- 6.79 GB
Measured Estimated VRAM 8 GB+
-
33.2B
llm-jp
llm-jp-4.1-33b-thinking
- Q4_K_M size
- 20.4 GB
- Memory at 8K
- 23.5 GB
Measured Estimated VRAM 24 GB+
-
8.6B
llm-jp
llm-jp-4.1-8b-thinking
- Q4_K_M size
- 5.50 GB
- Memory at 8K
- 7.51 GB
Measured Estimated VRAM 8 GB+
-
8.2B
tokyotech-llm
Qwen3-Swallow-8B-RL-v0.2
- Q4_K_M size
- 5.03 GB
- Memory at 8K
- 7.08 GB
Measured Estimated VRAM 8 GB+
-
6.7B
tokyotech-llm
Swallow-7b-NVE-instruct-hf
- Q4_K_M size
- 4.08 GB
- Memory at 8K
- -
Measured Estimated
-
3.4B
sbintuitions
sarashina2.2-3b-instruct-v0.1
- Q4_K_M size
- 2.07 GB
- Memory at 8K
- 4.16 GB
Measured Estimated VRAM 4 GB+
-
8.6B
llm-jp
llm-jp-4-8b-instruct
- Q4_K_M size
- 5.30 GB
- Memory at 8K
- 7.32 GB
Measured Estimated VRAM 8 GB+
-
116.8B
tokyotech-llm
GPT-OSS-Swallow-120B-RL-v0.1
- Q4_K_M size
- 87.9 GB
- Memory at 8K
- 89.1 GB
Measured Estimated VRAM 96 GB+
-
14.7B
shisa-ai
shisa-v2.1-unphi4-14b
- Q4_K_M size
- 8.89 GB
- Memory at 8K
- 11.3 GB
Measured Estimated VRAM 12 GB+
-
8.2B
shisa-ai
shisa-v2.1-qwen3-8b
- Q4_K_M size
- 5.03 GB
- Memory at 8K
- 7.08 GB
Measured Estimated VRAM 8 GB+
-
0.4B
shisa-ai
shisa-v2.1c-lfm2-350m
- Q4_K_M size
- 0.23 GB
- Memory at 8K
- 1.00 GB
Measured Estimated VRAM 4 GB+
-
13.7B
llm-jp
llm-jp-3.1-13b-instruct4
- Q4_K_M size
- 8.35 GB
- Memory at 8K
- -
Measured Estimated
-
2.6B
pfnet
plamo-3-nict-2b-base
- Q4_K_M size
- 1.65 GB
- Memory at 8K
- -
Measured Estimated
-
6.8B
tokyotech-llm
Swallow-7b-hf
- Q4_K_M size
- 4.14 GB
- Memory at 8K
- -
Measured Estimated
-
8B
elyza
Llama-3-ELYZA-JP-8B
- Q4_K_M size
- 4.92 GB
- Memory at 8K
- 6.79 GB
Measured Estimated VRAM 8 GB+
-
6.8B
tokyotech-llm
Swallow-7b-instruct-v0.1
- Q4_K_M size
- 4.14 GB
- Memory at 8K
- -
Measured Estimated
-
69B
tokyotech-llm
Swallow-70b-NVE-instruct-hf
- Q4_K_M size
- 41.4 GB
- Memory at 8K
- -
Measured Estimated
-
6.7B
tokyotech-llm
Swallow-7b-NVE-hf
- Q4_K_M size
- 4.08 GB
- Memory at 8K
- -
Measured Estimated
-
7.3B
llm-jp
llm-jp-3-7.2b-instruct3
- Q4_K_M size
- 4.47 GB
- Memory at 8K
- -
Measured Estimated
-
69.2B
tokyotech-llm
Swallow-70b-instruct-v0.1
- Q4_K_M size
- 41.5 GB
- Memory at 8K
- -
Measured Estimated
-
3.8B
llm-jp
llm-jp-3-3.7b-instruct3
- Q4_K_M size
- 2.33 GB
- Memory at 8K
- -
Measured Estimated
-
13.1B
elyza
ELYZA-japanese-Llama-2-13b-fast-instruct
- Q4_K_M size
- 7.96 GB
- Memory at 8K
- -
Measured Estimated
-
1.9B
llm-jp
llm-jp-3.1-1.8b-instruct4
- Q4_K_M size
- 1.16 GB
- Memory at 8K
- -
Measured Estimated
-
69.2B
tokyotech-llm
Swallow-70b-instruct-hf
- Q4_K_M size
- 41.5 GB
- Memory at 8K
- -
Measured Estimated
-
9.3B
llm-jp
llm-jp-3-8x1.8b-instruct3
- Q4_K_M size
- 5.75 GB
- Memory at 8K
- -
Measured Estimated
-
20.9B
tokyotech-llm
GPT-OSS-Swallow-20B-RL-v0.1
- Q4_K_M size
- 15.8 GB
- Memory at 8K
- 17.0 GB
Measured Estimated VRAM 16 GB+
-
1.4B
sbintuitions
sarashina2.2-1b-instruct-v0.1
- Q4_K_M size
- 0.93 GB
- Memory at 8K
- 2.38 GB
Measured Estimated VRAM 4 GB+
-
46.7B
tokyotech-llm
Swallow-MX-8x7b-NVE-v0.1
- Q4_K_M size
- 28.4 GB
- Memory at 8K
- -
Measured Estimated
-
20.9B
tokyotech-llm
GPT-OSS-Swallow-20B-SFT-v0.1
- Q4_K_M size
- 15.8 GB
- Memory at 8K
- 17.0 GB
Measured Estimated VRAM 16 GB+
-
8.2B
tokyotech-llm
Qwen3-Swallow-8B-SFT-v0.2
- Q4_K_M size
- 5.03 GB
- Memory at 8K
- 7.08 GB
Measured Estimated VRAM 8 GB+
-
7.3B
tokyotech-llm
Swallow-MS-7b-v0.1
- Q4_K_M size
- 4.43 GB
- Memory at 8K
- -
Measured Estimated
-
69.2B
tokyotech-llm
Swallow-70b-hf
- Q4_K_M size
- 41.5 GB
- Memory at 8K
- -
Measured Estimated
-
70.6B
tokyotech-llm
Llama-3-Swallow-70B-v0.1
- Q4_K_M size
- 42.5 GB
- Memory at 8K
- 46.0 GB
Measured Estimated VRAM 48 GB+
-
8.6B
llm-jp
llm-jp-4-8b-thinking
- Q4_K_M size
- 5.30 GB
- Memory at 8K
- 7.32 GB
Measured Estimated VRAM 8 GB+
-
46.7B
karakuri-ai
karakuri-lm-8x7b-instruct-v0.1
- Q4_K_M size
- 28.4 GB
- Memory at 8K
- 30.1 GB
Measured Estimated VRAM 32 GB+
-
1.9B
llm-jp
llm-jp-3-1.8b-instruct3
- Q4_K_M size
- 1.16 GB
- Memory at 8K
- -
Measured Estimated
-
0.8B
sbintuitions
sarashina2.2-0.5b-instruct-v0.1
- Q4_K_M size
- 0.53 GB
- Memory at 8K
- 1.78 GB
Measured Estimated VRAM 4 GB+
-
3.2B
shisa-ai
shisa-v2.1-llama3.2-3b
- Q4_K_M size
- 2.02 GB
- Memory at 8K
- 3.76 GB
Measured Estimated VRAM 4 GB+
-
6.8B
tokyotech-llm
Swallow-7b-plus-hf
- Q4_K_M size
- 4.14 GB
- Memory at 8K
- -
Measured Estimated
-
14.8B
cyberagent
cyberagent-DeepSeek-R1-Distill-Qwen-14B-Japanese
- Q4_K_M size
- 8.99 GB
- Memory at 8K
- 11.7 GB
Measured Estimated VRAM 12 GB+
-
13.1B
tokyotech-llm
Swallow-13b-instruct-hf
- Q4_K_M size
- 7.95 GB
- Memory at 8K
- -
Measured Estimated
-
8.2B
tokyotech-llm
Qwen3-Swallow-8B-CPT-v0.2
- Q4_K_M size
- 5.03 GB
- Memory at 8K
- 7.08 GB
Measured Estimated VRAM 8 GB+
-
13.1B
tokyotech-llm
Swallow-13b-hf
- Q4_K_M size
- 7.95 GB
- Memory at 8K
- -
Measured Estimated
-
33.2B
elyza
ELYZA-Thinking-1.0-llm-jp-4-33b
- Q4_K_M size
- 20.2 GB
- Memory at 8K
- 23.3 GB
Measured Estimated VRAM 24 GB+
-
7.6B
lightblue
DeepSeek-R1-Distill-Qwen-7B-Japanese
- Q4_K_M size
- 4.68 GB
- Memory at 8K
- 6.00 GB
Measured Estimated VRAM 6 GB+
-
32.8B
elyza
ELYZA-Thinking-1.0-Qwen-32B
- Q4_K_M size
- 19.9 GB
- Memory at 8K
- 22.8 GB
Measured Estimated VRAM 24 GB+
-
7.2B
karakuri-ai
karakuri-lm-7b-apm-v0.2
- Q4_K_M size
- 4.37 GB
- Memory at 8K
- 6.04 GB
Measured Estimated VRAM 6 GB+
-
70.6B
tokyotech-llm
Llama-3.3-Swallow-70B-Instruct-v0.4
- Q4_K_M size
- 42.5 GB
- Memory at 8K
- 46.0 GB
Measured Estimated VRAM 48 GB+
-
32.8B
tokyotech-llm
Qwen3-Swallow-32B-RL-v0.2
- Q4_K_M size
- 19.8 GB
- Memory at 8K
- 22.8 GB
Measured Estimated VRAM 24 GB+
-
0.8B
sbintuitions
sarashina2.2-0.5b
- Q4_K_M size
- 0.53 GB
- Memory at 8K
- 1.78 GB
Measured Estimated VRAM 4 GB+
-
6.8B
tokyotech-llm
Swallow-7b-instruct-hf
- Q4_K_M size
- 4.14 GB
- Memory at 8K
- -
Measured Estimated
-
13.1B
pfnet
plamo-13b-instruct
- Q4_K_M size
- 7.89 GB
- Memory at 8K
- -
Measured Estimated
-
70.6B
shisa-ai
shisa-v2.1-llama3.3-70b
- Q4_K_M size
- 42.5 GB
- Memory at 8K
- 46.0 GB
Measured Estimated VRAM 48 GB+
-
70.6B
tokyotech-llm
Llama-3-Swallow-70B-Instruct-v0.1
- Q4_K_M size
- 42.5 GB
- Memory at 8K
- 46.0 GB
Measured Estimated VRAM 48 GB+
-
13.1B
tokyotech-llm
Swallow-13b-instruct-v0.1
- Q4_K_M size
- 7.95 GB
- Memory at 8K
- -
Measured Estimated
-
7.6B
abeja
ABEJA-Qwen2.5-7b-Japanese-v0.1
- Q4_K_M size
- 4.68 GB
- Memory at 8K
- 6.00 GB
Measured Estimated VRAM 6 GB+
-
30.5B
tokyotech-llm
Qwen3-Swallow-30B-A3B-RL-v0.2
- Q4_K_M size
- 18.6 GB
- Memory at 8K
- 20.2 GB
Measured Estimated VRAM 24 GB+
-
69B
tokyotech-llm
Swallow-70b-NVE-hf
- Q4_K_M size
- 41.4 GB
- Memory at 8K
- -
Measured Estimated
-
1B
llm-jp
llm-jp-3-980m-instruct3
- Q4_K_M size
- 0.63 GB
- Memory at 8K
- -
Measured Estimated
-
8B
lightblue
suzume-llama-3-8B-japanese
- Q4_K_M size
- 4.92 GB
- Memory at 8K
- 6.79 GB
Measured Estimated VRAM 8 GB+
-
8B
tokyotech-llm
Llama-3-Swallow-8B-v0.1
- Q4_K_M size
- 4.92 GB
- Memory at 8K
- 6.79 GB
Measured Estimated VRAM 8 GB+
-
70.6B
tokyotech-llm
Llama-3.1-Swallow-70B-v0.1
- Q4_K_M size
- 42.5 GB
- Memory at 8K
- 46.0 GB
Measured Estimated VRAM 48 GB+
-
25.2B
shisa-ai
shisa-de-2
- Q4_K_M size
- 16.8 GB
- Memory at 8K
- 18.4 GB
Measured Estimated VRAM 24 GB+
-
27B
shisa-ai
ablation-196-finalsft2-shisa-v2-gemma3-27b
- Q4_K_M size
- 16.5 GB
- Memory at 8K
- 18.9 GB
Measured Estimated VRAM 24 GB+
-
32.1B
elyza
ELYZA-Thinking-1.0-llm-jp-4-32b-a3b
- Q4_K_M size
- 21.4 GB
- Memory at 8K
- 22.9 GB
Measured Estimated VRAM 24 GB+
-
9.2B
tokyotech-llm
Gemma-2-Llama-Swallow-9b-pt-v0.1
- Q4_K_M size
- 5.76 GB
- Memory at 8K
- 9.02 GB
Measured Estimated VRAM 12 GB+
-
7.6B
elyza
ELYZA-Shortcut-1.0-Qwen-7B
- Q4_K_M size
- 4.68 GB
- Memory at 8K
- 6.00 GB
Measured Estimated VRAM 6 GB+
-
25.2B
shisa-ai
shisa-de-2.1
- Q4_K_M size
- 16.8 GB
- Memory at 8K
- 18.4 GB
Measured Estimated VRAM 24 GB+
-
8B
shisa-ai
shisa-v1-llama3-8b
- Q4_K_M size
- 4.92 GB
- Memory at 8K
- 6.79 GB
Measured Estimated VRAM 8 GB+
-
9.2B
tokyotech-llm
Gemma-2-Llama-Swallow-9b-it-v0.1
- Q4_K_M size
- 5.76 GB
- Memory at 8K
- 9.02 GB
Measured Estimated VRAM 12 GB+
-
69.2B
karakuri-ai
karakuri-lm-70b-chat-v0.1
- Q4_K_M size
- 41.6 GB
- Memory at 8K
- -
Measured Estimated
-
27.2B
tokyotech-llm
Gemma-2-Llama-Swallow-27b-pt-v0.1
- Q4_K_M size
- 16.6 GB
- Memory at 8K
- 20.1 GB
Measured Estimated VRAM 24 GB+
-
12.2B
shisa-ai
shisa-v2-mistral-nemo-12b
- Q4_K_M size
- 7.48 GB
- Memory at 8K
- 9.62 GB
Measured Estimated VRAM 12 GB+
-
13B
tokyotech-llm
Swallow-13b-NVE-hf
- Q4_K_M size
- 7.87 GB
- Memory at 8K
- -
Measured Estimated
-
8B
tokyotech-llm
Llama-3.1-Swallow-8B-v0.1
- Q4_K_M size
- 4.92 GB
- Memory at 8K
- 6.79 GB
Measured Estimated VRAM 8 GB+
-
3.4B
sbintuitions
sarashina2.2-vision-3b
- Q4_K_M size
- 2.07 GB
- Memory at 8K
- 4.16 GB
Measured Estimated VRAM 4 GB+
-
32.8B
shisa-ai
shisa-v2-qwen2.5-32b
- Q4_K_M size
- 19.9 GB
- Memory at 8K
- 22.8 GB
Measured Estimated VRAM 24 GB+
-
70.6B
shisa-ai
shisa-v2-llama3.3-70b
- Q4_K_M size
- 42.5 GB
- Memory at 8K
- 46.0 GB
Measured Estimated VRAM 48 GB+
-
8B
tokyotech-llm
Llama-3.1-Swallow-8B-v0.5
- Q4_K_M size
- 4.92 GB
- Memory at 8K
- 6.79 GB
Measured Estimated VRAM 8 GB+
-
23.6B
shisa-ai
shisa-v2-mistral-small-24b
- Q4_K_M size
- 14.3 GB
- Memory at 8K
- 16.5 GB
Measured Estimated VRAM 16 GB+
-
1.4B
sbintuitions
sarashina2.2-1b
- Q4_K_M size
- 0.93 GB
- Memory at 8K
- 2.38 GB
Measured Estimated VRAM 4 GB+
-
7.6B
lightblue
lightblue-DeepSeek-R1-Distill-Qwen-7B-Japanese
- Q4_K_M size
- 4.68 GB
- Memory at 8K
- 6.23 GB
Measured Estimated VRAM 6 GB+
-
32.8B
tokyotech-llm
Qwen3-Swallow-32B-SFT-v0.2
- Q4_K_M size
- 19.8 GB
- Memory at 8K
- 22.8 GB
Measured Estimated VRAM 24 GB+
-
25.2B
shisa-ai
shisa-de-1
- Q4_K_M size
- 16.8 GB
- Memory at 8K
- 18.4 GB
Measured Estimated VRAM 24 GB+
-
30.5B
tokyotech-llm
Qwen3-Swallow-30B-A3B-SFT-v0.2
- Q4_K_M size
- 18.6 GB
- Memory at 8K
- 20.2 GB
Measured Estimated VRAM 24 GB+
-
8.5B
karakuri-ai
karakuri-lm-7b-apm-v0.1
- Q4_K_M size
- 5.33 GB
- Memory at 8K
- 10.2 GB
Measured Estimated VRAM 12 GB+
-
8B
tokyotech-llm
Llama-3.1-Swallow-8B-Instruct-v0.2
- Q4_K_M size
- 4.92 GB
- Memory at 8K
- 6.79 GB
Measured Estimated VRAM 8 GB+
-
12.2B
cyberagent
cyberagent-Mistral-Nemo-Japanese-Instruct-2408
- Q4_K_M size
- 7.48 GB
- Memory at 8K
- 9.62 GB
Measured Estimated VRAM 12 GB+
-
27.2B
tokyotech-llm
Gemma-2-Llama-Swallow-27b-it-v0.1
- Q4_K_M size
- 16.6 GB
- Memory at 8K
- 20.1 GB
Measured Estimated VRAM 24 GB+
-
23.6B
shisa-ai
ablation-195-finalsft2-shisa-v2-mistral-small-24b
- Q4_K_M size
- 14.3 GB
- Memory at 8K
- 16.5 GB
Measured Estimated VRAM 16 GB+
-
32.8B
cyberagent
cyberagent-DeepSeek-R1-Distill-Qwen-32B-Japanese
- Q4_K_M size
- 19.9 GB
- Memory at 8K
- 23.1 GB
Measured Estimated VRAM 24 GB+
-
8B
tokyotech-llm
Llama-3.1-Swallow-8B-v0.2
- Q4_K_M size
- 4.92 GB
- Memory at 8K
- 6.79 GB
Measured Estimated VRAM 8 GB+
-
7.6B
shisa-ai
shisa-v2-qwen2.5-7b
- Q4_K_M size
- 4.68 GB
- Memory at 8K
- 6.00 GB
Measured Estimated VRAM 6 GB+
-
12.2B
cyberagent
Mistral-Nemo-Japanese-Instruct-2408
- Q4_K_M size
- 7.48 GB
- Memory at 8K
- 9.62 GB
Measured Estimated VRAM 12 GB+
-
8B
shisa-ai
shisa-v2-llama3.1-8b
- Q4_K_M size
- 4.92 GB
- Memory at 8K
- 6.79 GB
Measured Estimated VRAM 8 GB+
-
32.8B
abeja
ABEJA-QwQ32b-Reasoning-Japanese-v1.0
- Q4_K_M size
- 19.9 GB
- Memory at 8K
- 22.8 GB
Measured Estimated VRAM 24 GB+
-
8B
tokyotech-llm
Llama-3-Swallow-8B-Instruct-v0.1
- Q4_K_M size
- 4.92 GB
- Memory at 8K
- 6.79 GB
Measured Estimated VRAM 8 GB+
-
46.7B
karakuri-ai
karakuri-lm-8x7b-chat-v0.1
- Q4_K_M size
- 28.4 GB
- Memory at 8K
- 30.1 GB
Measured Estimated VRAM 32 GB+
-
8B
shisa-ai
031-swallow-8b-0.5-base-v2new-dpo405b
- Q4_K_M size
- 4.92 GB
- Memory at 8K
- 6.79 GB
Measured Estimated VRAM 8 GB+
-
13.2B
stockmark
stockmark-13b
- Q4_K_M size
- 8.00 GB
- Memory at 8K
- -
Measured Estimated
-
13.1B
pfnet
plamo-13b-instruct-nc
- Q4_K_M size
- 7.89 GB
- Memory at 8K
- -
Measured Estimated
-
0.9B
pfnet
plamo-3-610m-fin-instruct
- Q4_K_M size
- 0.57 GB
- Memory at 8K
- 1.36 GB
Measured Estimated VRAM 4 GB+
-
70.6B
shisa-ai
shisa-v1-llama3-70b
- Q4_K_M size
- 42.5 GB
- Memory at 8K
- 46.0 GB
Measured Estimated VRAM 48 GB+
-
14B
shisa-ai
shisa-v1-phi3-14b
- Q4_K_M size
- 8.57 GB
- Memory at 8K
- 10.8 GB
Measured Estimated VRAM 12 GB+
-
14.8B
cyberagent
DeepSeek-R1-Distill-Qwen-14B-Japanese
- Q4_K_M size
- 8.99 GB
- Memory at 8K
- 11.4 GB
Measured Estimated VRAM 12 GB+
-
32.8B
karakuri-ai
karakuri-vl-32b-thinking-2507-exp
- Q4_K_M size
- 19.9 GB
- Memory at 8K
- 22.8 GB
Measured Estimated VRAM 24 GB+
-
32.8B
abeja
ABEJA-Qwen2.5-32b-Japanese-v0.1
- Q4_K_M size
- 19.9 GB
- Memory at 8K
- 22.8 GB
Measured Estimated VRAM 24 GB+
-
2.6B
rinna
gemma-2-baku-2b
- Q4_K_M size
- 1.71 GB
- Memory at 8K
- 3.45 GB
Measured Estimated VRAM 4 GB+
-
14.7B
shisa-ai
shisa-v2-unphi4-14b
- Q4_K_M size
- 8.89 GB
- Memory at 8K
- 11.3 GB
Measured Estimated VRAM 12 GB+
-
32.8B
karakuri-ai
karakuri-lm-32b-thinking-2501-exp
- Q4_K_M size
- 19.9 GB
- Memory at 8K
- 22.8 GB
Measured Estimated VRAM 24 GB+
-
8B
shisa-ai
shisa-v1-llama3-8b.2e5
- Q4_K_M size
- 4.92 GB
- Memory at 8K
- 6.79 GB
Measured Estimated VRAM 8 GB+
-
96B
stockmark
Stockmark-2-100B-Instruct-beta
- IQ1_S size
- 20.5 GB
- Memory at 8K
- -
Measured Estimated
-
1.2B
shisa-ai
shisa-v2.1-lfm2-1.2b
- Q4_K_M size
- 0.73 GB
- Memory at 8K
- 1.50 GB
Measured Estimated VRAM 4 GB+
-
73.2B
llm-jp
llm-jp-3-8x13b-instruct3
- Q4_K_M size
- 45.4 GB
- Memory at 8K
- -
Measured Estimated
-
1.4B
sbintuitions
sarashina2.1-1b
- Q4_K_M size
- 0.93 GB
- Memory at 8K
- 2.38 GB
Measured Estimated VRAM 4 GB+
-
8.1B
pfnet
plamo-3-nict-8b-base
- Q4_K_M size
- 5.03 GB
- Memory at 8K
- -
Measured Estimated
-
8.2B
karakuri-ai
karakuri-vl-2-8b-thinking-2603
- Q4_K_M size
- 5.03 GB
- Memory at 8K
- 7.08 GB
Measured Estimated VRAM 8 GB+
-
2.6B
rinna
gemma-2-baku-2b-it
- Q4_K_M size
- 1.71 GB
- Memory at 8K
- 3.45 GB
Measured Estimated VRAM 4 GB+
-
8B
rinna
llama-3-youko-8b-instruct
- Q4_K_M size
- 4.92 GB
- Memory at 8K
- 6.79 GB
Measured Estimated VRAM 8 GB+
-
8B
shisa-ai
shisa-v1-7b-v2.1
- Q4_K_M size
- 4.87 GB
- Memory at 8K
- 6.73 GB
Measured Estimated VRAM 8 GB+
-
73.2B
llm-jp
llm-jp-3.1-8x13b-instruct4
- Q4_K_M size
- 45.4 GB
- Memory at 8K
- -
Measured Estimated
-
32.1B
llm-jp
llm-jp-4-32b-a3b-thinking
- Q4_K_M size
- 21.4 GB
- Memory at 8K
- 23.0 GB
Measured Estimated VRAM 24 GB+
-
32.8B
karakuri-ai
karakuri-vl-32b-instruct-2507
- Q4_K_M size
- 19.9 GB
- Memory at 8K
- 22.8 GB
Measured Estimated VRAM 24 GB+
-
405.9B
shisa-ai
shisa-v2-llama3.1-405b
- Q4_K_M size
- 243 GB
- Memory at 8K
- 248 GB
Measured Estimated
-
13.1B
pfnet
plamo-13b
- Q4_K_M size
- 7.89 GB
- Memory at 8K
- -
Measured Estimated
-
13.7B
llm-jp
llm-jp-3-13b-instruct3
- Q4_K_M size
- 8.35 GB
- Memory at 8K
- -
Measured Estimated
-
8B
rinna
llama-3-youko-8b
- Q4_K_M size
- 4.92 GB
- Memory at 8K
- 6.79 GB
Measured Estimated VRAM 8 GB+
-
32.8B
elyza
ELYZA-Shortcut-1.0-Qwen-32B
- Q4_K_M size
- 19.9 GB
- Memory at 8K
- 22.8 GB
Measured Estimated VRAM 24 GB+
-
0.8B
sbintuitions
sarashina2.2-tts
- Q4_K_M size
- 0.54 GB
- Memory at 8K
- 1.80 GB
Measured Estimated VRAM 4 GB+
-
96B
stockmark
Stockmark-2-100B-Instruct
- Q4_K_M size
- 57.6 GB
- Memory at 8K
- 61.2 GB
Measured Estimated VRAM 64 GB+
-
69.2B
karakuri-ai
karakuri-lm-70b-v0.1
- Q4_K_M size
- 41.6 GB
- Memory at 8K
- -
Measured Estimated
-
70.6B
rinna
llama-3-youko-70b-instruct
- Q4_K_M size
- 42.5 GB
- Memory at 8K
- 46.0 GB
Measured Estimated VRAM 48 GB+
-
8B
shisa-ai
ablation-206-a163.finaldpo2.8e8.constant-shisa-v2-llama-3.1-8b
- Q4_K_M size
- 4.92 GB
- Memory at 8K
- 6.79 GB
Measured Estimated VRAM 8 GB+
-
32.8B
rinna
qwq-bakeneko-32b
- Q2_K size
- 12.3 GB
- Memory at 8K
- 15.3 GB
Measured Estimated VRAM 16 GB+
-
7.2B
shisa-ai
029-shisa-gamma-7b-v1-v2new-dpo405b
- Q4_K_M size
- 4.37 GB
- Memory at 8K
- 6.04 GB
Measured Estimated VRAM 6 GB+
-
8B
shisa-ai
ablation-88-a83.dpo.armorm-shisa-v2-llama-3.1-8b
- Q4_K_M size
- 4.92 GB
- Memory at 8K
- 6.79 GB
Measured Estimated VRAM 8 GB+
-
8B
shisa-ai
ablation-27-rafathenev2.9epochs-shisa-v2-llama-3.1-8b-lr8e6
- Q4_K_M size
- 4.92 GB
- Memory at 8K
- 6.79 GB
Measured Estimated VRAM 8 GB+
-
12.2B
shisa-ai
ablation-152-finalsft-shisa-v2-mistral-nemo-japanese-12b
- Q4_K_M size
- 7.48 GB
- Memory at 8K
- 9.62 GB
Measured Estimated VRAM 12 GB+
-
7.6B
shisa-ai
ablation-191-finalsft2-shisa-v2-qwen2.5-7b
- Q4_K_M size
- 4.68 GB
- Memory at 8K
- 6.00 GB
Measured Estimated VRAM 6 GB+
-
13.7B
llm-jp
llm-jp-3-13b-instruct
- Q4_K_M size
- 8.35 GB
- Memory at 8K
- -
Measured Estimated
-
8B
shisa-ai
ablation-14-ratulu405b-shisa-v2-llama-3.1-8b-lr8e6
- Q4_K_M size
- 4.92 GB
- Memory at 8K
- 6.79 GB
Measured Estimated VRAM 8 GB+
-
12.2B
shisa-ai
ablation-178-finalsft2-shisa-v2-mistral-nemo-japanese-12b
- Q4_K_M size
- 7.48 GB
- Memory at 8K
- 9.62 GB
Measured Estimated VRAM 12 GB+
-
8B
shisa-ai
ablation-168-a163.dpo.finaldpo.if25-shisa-v2-llama-3.1-8b
- Q4_K_M size
- 4.92 GB
- Memory at 8K
- 6.79 GB
Measured Estimated VRAM 8 GB+
-
8B
shisa-ai
ablation-46-rafathenev2.rp-shisa-v2-llama-3.1-8b-lr8e6
- Q4_K_M size
- 4.92 GB
- Memory at 8K
- 6.79 GB
Measured Estimated VRAM 8 GB+
-
14.7B
shisa-ai
ablation-73-rafathenev2.rp.tl.unphi42e6-shisa-v2-unphi-4-14b
- Q4_K_M size
- 8.89 GB
- Memory at 8K
- 11.3 GB
Measured Estimated VRAM 12 GB+
-
8B
shisa-ai
ablation-174-shisav2.if50.tltweak-shisa-v2-llama-3.1-8b
- Q4_K_M size
- 4.92 GB
- Memory at 8K
- 6.79 GB
Measured Estimated VRAM 8 GB+
-
12.2B
shisa-ai
ablation-123-a114.dpo.armorm.rp-shisa-v2-mistral-nemo-12b
- Q4_K_M size
- 7.48 GB
- Memory at 8K
- 9.62 GB
Measured Estimated VRAM 12 GB+
-
8B
shisa-ai
ablation-57-rafathenev2.rp.tl.shisav1-shisa-v2-shisa-base-7b-v1
- Q4_K_M size
- 4.87 GB
- Memory at 8K
- 6.73 GB
Measured Estimated VRAM 8 GB+
-
8B
shisa-ai
ablation-38-rafathenev2.cmrmix.fixedlength-shisa-v2-llama-3.1-8b-lr8e6
- Q4_K_M size
- 4.92 GB
- Memory at 8K
- 6.79 GB
Measured Estimated VRAM 8 GB+
-
8B
shisa-ai
ablation-59-a55.dpo.en-shisa-v2-llama-3.1-8b
- Q4_K_M size
- 4.92 GB
- Memory at 8K
- 6.79 GB
Measured Estimated VRAM 8 GB+
-
8B
shisa-ai
ablation-163-shisav2.if50-shisa-v2-llama-3.1-8b
- Q4_K_M size
- 4.92 GB
- Memory at 8K
- 6.79 GB
Measured Estimated VRAM 8 GB+
-
8B
shisa-ai
ablation-36-cmrmix-shisa-v2-llama-3.1-8b-lr8e6
- Q4_K_M size
- 4.92 GB
- Memory at 8K
- 6.79 GB
Measured Estimated VRAM 8 GB+
-
8B
shisa-ai
ablation-72-a55.simpo.armorm.v2-shisa-v2-llama-3.1-8b
- Q4_K_M size
- 4.92 GB
- Memory at 8K
- 6.79 GB
Measured Estimated VRAM 8 GB+
-
8B
shisa-ai
ablation-00-baseline-shisa-v2-llama3-8b-lr8e6
- Q4_K_M size
- 4.92 GB
- Memory at 8K
- 6.79 GB
Measured Estimated VRAM 8 GB+
-
3.8B
llm-jp
llm-jp-3-3.7b-instruct
- Q4_K_M size
- 2.33 GB
- Memory at 8K
- -
Measured Estimated
-
8B
shisa-ai
ablation-26-reasoning.inputs-shisa-v2-llama-3.1-8b-lr8e6
- Q4_K_M size
- 4.92 GB
- Memory at 8K
- 6.79 GB
Measured Estimated VRAM 8 GB+
-
8B
shisa-ai
ablation-99-bestofn.atlo.rp.tlx-shisa-v2-llama-3.1-8b
- Q4_K_M size
- 4.92 GB
- Memory at 8K
- 6.79 GB
Measured Estimated VRAM 8 GB+
-
32.8B
rinna
qwen2.5-bakeneko-32b-instruct
- Q2_K size
- 12.3 GB
- Memory at 8K
- 15.3 GB
Measured Estimated VRAM 16 GB+
-
8B
shisa-ai
ablation-08-rallama33-shisa-v2-llama-3.1-8b-lr8e6
- Q4_K_M size
- 4.92 GB
- Memory at 8K
- 6.79 GB
Measured Estimated VRAM 8 GB+
-
8B
shisa-ai
ablation-61-a55.dpo.enjanot-shisa-v2-llama-3.1-8b
- Q4_K_M size
- 4.92 GB
- Memory at 8K
- 6.79 GB
Measured Estimated VRAM 8 GB+
-
8B
shisa-ai
ablation-199-a169-expo-shisa-v2-llama-3.1-8b
- Q4_K_M size
- 4.92 GB
- Memory at 8K
- 6.79 GB
Measured Estimated VRAM 8 GB+
-
8B
shisa-ai
ablation-158-a128.dpo.finaldpo.if50-shisa-v2-llama-3.1-8b
- Q4_K_M size
- 4.92 GB
- Memory at 8K
- 6.79 GB
Measured Estimated VRAM 8 GB+
-
70.1B
sbintuitions
sarashina2-70b
- Q4_K_M size
- 42.2 GB
- Memory at 8K
- 45.7 GB
Measured Estimated VRAM 48 GB+
-
32.8B
rinna
deepseek-r1-distill-qwen2.5-bakeneko-32b
- Q2_K size
- 12.3 GB
- Memory at 8K
- 15.3 GB
Measured Estimated VRAM 16 GB+
-
8B
shisa-ai
ablation-49-rafathenev2.magpief-shisa-v2-llama-3.1-8b
- Q4_K_M size
- 4.92 GB
- Memory at 8K
- 6.79 GB
Measured Estimated VRAM 8 GB+
-
13B
elyza
ELYZA-japanese-Llama-2-13b
- Q2_K size
- 4.85 GB
- Memory at 8K
- -
Measured Estimated
-
32.8B
rinna
qwen2.5-bakeneko-32b-instruct-v2
- Q4_K_M size
- 19.9 GB
- Memory at 8K
- 23.1 GB
Measured Estimated VRAM 24 GB+
-
1.2B
sbintuitions
sarashina-embedding-v2-1b
- Q4_K_M size
- 0.83 GB
- Memory at 8K
- 2.28 GB
Measured Estimated VRAM 4 GB+
-
7.6B
elyza
ELYZA-Diffusion-Instruct-1.0-Dream-7B
- Q4_K_M size
- 4.68 GB
- Memory at 8K
- 5.76 GB
Measured Estimated VRAM 6 GB+
Derivatives tuned for Japanese
Models based on non-Japanese models whose names say they were further trained for Japanese (names containing Japanese or JP).
-
4.1B
soyaakinohara
Spark-X2.5-4B-Heretic-jp
- Q4_K_M size
- 2.60 GB
- Memory at 8K
- 3.82 GB
Measured Estimated VRAM 4 GB+
-
32.1B
OS-Software
llm-jp-4.1-32b-a3b-thinking-uncensored-heretic
- Q4_K_M size
- 21.5 GB
- Memory at 8K
- 23.0 GB
Measured Estimated VRAM 24 GB+
-
7.2B
stabilityai
japanese-stablelm-instruct-gamma-7b
- Q4_K_M size
- 4.37 GB
- Memory at 8K
- 6.04 GB
Measured Estimated VRAM 6 GB+
-
4.2B
dahara1
Qwen3.5-4B-UD-japanese-imatrix
- Q4_K_M size
- 2.74 GB
- Memory at 8K
- 4.11 GB
Measured Estimated VRAM 4 GB+
-
8B
mmnga
Llama-3-ELYZA-JP-8B
- Q4_K_M size
- 4.92 GB
- Memory at 8K
- 6.79 GB
Measured Estimated VRAM 8 GB+
-
6.7B
stabilityai
japanese-stablelm-instruct-beta-7b
- Q4_K_M size
- 4.08 GB
- Memory at 8K
- -
Measured Estimated
-
4.6B
dahara1
gemma-4-E2B-it-UD-japanese-imatrix
- Q4_K_M size
- 3.11 GB
- Memory at 8K
- 4.24 GB
Measured Estimated VRAM 4 GB+
-
69B
stabilityai
japanese-stablelm-instruct-beta-70b
- Q4_K_M size
- 41.4 GB
- Memory at 8K
- -
Measured Estimated
-
8.9B
urufura
NVIDIA-Nemotron-Nano-9B-v2-Japanese
- Q4_K_M size
- 6.53 GB
- Memory at 8K
- 7.61 GB
Measured Estimated VRAM 8 GB+
-
20.9B
OS-Software
gemma-4-26B-A4B-it-qat-q4_0-heretic-japanese-pruned
- Q4_0 size
- 8.61 GB
- Memory at 8K
- 10.2 GB
Measured Estimated VRAM 12 GB+
-
8.9B
nvidia
NVIDIA-Nemotron-Nano-9B-v2-Japanese
- Q4_K_M size
- 6.53 GB
- Memory at 8K
- 7.61 GB
Measured Estimated VRAM 8 GB+
-
6.8B
mmnga
ELYZA-japanese-Llama-2-7b-fast-instruct
- Q4_K_M size
- 4.16 GB
- Memory at 8K
- -
Measured Estimated
-
7.2B
mmnga
umiyuki-Japanese-Chat-Umievo-itr001-7b
- Q4_K_M size
- 4.37 GB
- Memory at 8K
- -
Measured Estimated
-
8B
mmnga
haqishen-Llama-3-8B-Japanese-Instruct
- Q4_K_M size
- 4.92 GB
- Memory at 8K
- 6.79 GB
Measured Estimated VRAM 8 GB+
-
9B
dahara1
Qwen3.5-9B-UD-japanese-imatrix
- Q4_K_M size
- 5.72 GB
- Memory at 8K
- 7.11 GB
Measured Estimated VRAM 8 GB+
-
11.9B
dahara1
gemma-4-12B-it-qat-UD-japanese-imatrix
- Q4_K_M size
- 7.12 GB
- Memory at 8K
- 8.83 GB
Measured Estimated VRAM 12 GB+
-
8B
mmnga
lightblue-suzume-llama-3-8B-japanese
- Q4_K_M size
- 4.92 GB
- Memory at 8K
- 6.79 GB
Measured Estimated VRAM 8 GB+
-
8.2B
dahara1
shisa-v2.1-qwen3-8b-UD-japanese-imatrix
- Q4_K_M size
- 5.03 GB
- Memory at 8K
- 7.08 GB
Measured Estimated VRAM 8 GB+
-
7.2B
RichardErkhov
stabilityai_-_japanese-stablelm-base-gamma-7b
- Q4_K_M size
- 4.37 GB
- Memory at 8K
- -
Measured Estimated
-
69B
stabilityai
japanese-stablelm-base-beta-70b
- Q4_K_M size
- 41.4 GB
- Memory at 8K
- -
Measured Estimated
-
70.6B
mmnga
Llama-3.1-70B-Japanese-Instruct-2407
- Q4_K_M size
- 42.5 GB
- Memory at 8K
- 46.0 GB
Measured Estimated VRAM 48 GB+
-
6.1B
mmnga
aibuncho-japanese-novel-gpt-j-6b
- Q4_K_M size
- 3.70 GB
- Memory at 8K
- -
Measured Estimated
-
30.5B
NandemoGHS
Anime-Speech-Japanese-Captioner
- Q4_K_M size
- 18.6 GB
- Memory at 8K
- 20.2 GB
Measured Estimated VRAM 24 GB+
-
7.5B
dahara1
gemma-4-E4B-it-UD-japanese-imatrix
- Q4_K_M size
- 4.98 GB
- Memory at 8K
- 6.23 GB
Measured Estimated VRAM 6 GB+
-
1.6B
mmnga
japanese-stablelm-2-instruct-1_6b
- Q4_K_M size
- 1.03 GB
- Memory at 8K
- -
Measured Estimated
-
7.2B
RichardErkhov
stabilityai_-_japanese-stablelm-instruct-gamma-7b
- Q4_K_M size
- 4.37 GB
- Memory at 8K
- -
Measured Estimated
-
8.6B
SousiOmine
Lumi-v2-llm-jp-4-8b
- Q4_K_M size
- 5.30 GB
- Memory at 8K
- 7.32 GB
Measured Estimated VRAM 8 GB+
-
30.7B
OS-Software
gemma-4-31B-it-qat-heretic-japanese-imatrix
- IQ2_XS size
- 9.02 GB
- Memory at 8K
- 12.0 GB
Measured Estimated VRAM 12 GB+
-
6.7B
mmnga
ELYZA-japanese-Llama-2-7b-instruct
- Q4_K_M size
- 4.08 GB
- Memory at 8K
- -
Measured Estimated
-
6.9B
sambanovasystems
SambaLingo-Japanese-Base
- Q4_K_M size
- 4.23 GB
- Memory at 8K
- -
Measured Estimated
-
33.2B
OS-Software
llm-jp-4.1-33b-thinking-uncensored-heretic
- Q4_K_M size
- 20.4 GB
- Memory at 8K
- 23.5 GB
Measured Estimated VRAM 24 GB+
-
1.9B
dahara1
Qwen3.5-2B-UD-japanese-imatrix
- Q4_K_M size
- 1.28 GB
- Memory at 8K
- 2.45 GB
Measured Estimated VRAM 4 GB+
-
32.8B
deep-analysis-research
D2IL-Japanese-Qwen2.5-32B-Instruct-v0.1
- Q4_K_M size
- 19.9 GB
- Memory at 8K
- 22.8 GB
Measured Estimated VRAM 24 GB+
-
1.8B
mmnga
line-corp-japanese-large-lm-1.7b
- Q4_K_M size
- 1.15 GB
- Memory at 8K
- -
Measured Estimated
-
8B
kg-b0mbe
Llama-3.1-8B-Japanese-Yamaguchi-Dialect
- Q4_K_M size
- 4.92 GB
- Memory at 8K
- 6.79 GB
Measured Estimated VRAM 8 GB+
-
3.2B
dahara1
shisa-v2.1-llama3.2-3b-UD-japanese-imatrix
- Q4_K_M size
- 2.02 GB
- Memory at 8K
- 3.76 GB
Measured Estimated VRAM 4 GB+
-
6.7B
mmnga
ELYZA-japanese-CodeLlama-7b
- Q4_K_M size
- 4.08 GB
- Memory at 8K
- 9.45 GB
Measured Estimated VRAM 12 GB+
-
6.7B
mmnga
ELYZA-japanese-Llama-2-7b
- Q4_K_M size
- 4.08 GB
- Memory at 8K
- -
Measured Estimated
-
8B
RichardErkhov
elyza_-_Llama-3-ELYZA-JP-8B
- Q4_K_M size
- 4.92 GB
- Memory at 8K
- 6.79 GB
Measured Estimated VRAM 8 GB+
-
13.1B
mmnga
llm-jp-13b-instruct-full-jaster-dolly-oasst-v1.0
- Q4_K_M size
- 8.39 GB
- Memory at 8K
- -
Measured Estimated
-
8B
mmnga
aixsatoshi-Llama-3-8b-Cosmopedia-japanese
- Q4_K_M size
- 4.92 GB
- Memory at 8K
- 6.79 GB
Measured Estimated VRAM 8 GB+
-
9B
Aikimi
Qwen3.5-9B-Japanese-awy
- Q4_K_M size
- 5.63 GB
- Memory at 8K
- 7.00 GB
Measured Estimated VRAM 8 GB+
-
0.8B
Takenoko12345678
Qwen3.5-0.8B-Japanese-SFT-v2.5
- Q4_K_M size
- 0.53 GB
- Memory at 8K
- 1.70 GB
Measured Estimated VRAM 4 GB+
-
70.6B
Saxo
Linkbricks-Horizon-AI-Japanese-Pro-V3-70B
- Q4_K_M size
- 42.5 GB
- Memory at 8K
- 46.0 GB
Measured Estimated VRAM 48 GB+
-
6.7B
mmnga
ELYZA-japanese-CodeLlama-7b-instruct
- Q4_K_M size
- 4.08 GB
- Memory at 8K
- 9.45 GB
Measured Estimated VRAM 12 GB+
-
8B
ChiKoi7
Llama-3-ELYZA-JP-8B-Heretic
- Q4_K_M size
- 4.92 GB
- Memory at 8K
- 6.79 GB
Measured Estimated VRAM 8 GB+
-
8B
aixsatoshi
Llama-3-8b-Cosmopedia-japanese
- Q4_K_M size
- 4.92 GB
- Memory at 8K
- 6.79 GB
Measured Estimated VRAM 8 GB+
-
11.8B
dahara1
gemma-3-12b-it-qat-japanese-imatrix
- Q4_K_M size
- 7.30 GB
- Memory at 8K
- 9.41 GB
Measured Estimated VRAM 12 GB+
-
4.1B
Takenoko12345678
Spark-X2.5-4B-Japanese
- Q4_K_M size
- 2.60 GB
- Memory at 8K
- 3.82 GB
Measured Estimated VRAM 4 GB+
-
32.8B
Saxo
Linkbricks-Horizon-AI-Japanese-Base-32B
- Q4_K_M size
- 19.9 GB
- Memory at 8K
- 22.8 GB
Measured Estimated VRAM 24 GB+
-
0.8B
Takenoko12345678
Qwen3.5-0.8B-Japanese-SFT-v2
- Q4_K_M size
- 0.53 GB
- Memory at 8K
- 1.70 GB
Measured Estimated VRAM 4 GB+
-
14.8B
flypg
DeepSeek-R1-Distill-Qwen-14B-Japanese-chat-quant
- Q4_K_M size
- 8.99 GB
- Memory at 8K
- 11.4 GB
Measured Estimated VRAM 12 GB+
-
13.1B
mmnga
ELYZA-japanese-Llama-2-13b-fast-instruct
- Q4_K_M size
- 7.96 GB
- Memory at 8K
- -
Measured Estimated
-
6.8B
mmnga
ELYZA-japanese-Llama-2-7b-fast
- Q4_K_M size
- 4.16 GB
- Memory at 8K
- -
Measured Estimated
-
7.2B
mmnga
japanese-stablelm-base-gamma-7b
- Q4_K_M size
- 4.37 GB
- Memory at 8K
- 6.52 GB
Measured Estimated VRAM 8 GB+
-
7.2B
MaziyarPanahi
japanese-stablelm-instruct-gamma-7b-Mistral-7B-Instruct-v0.2-slerp
- Q4_K_M size
- 4.37 GB
- Memory at 8K
- 6.04 GB
Measured Estimated VRAM 6 GB+
-
1.9B
Rikunarita-ORG
Qwen3.5-2B-Ideal-TSUNDERE-Loli-Girl-Japanese-v1
- Q4_K_M size
- 1.27 GB
- Memory at 8K
- 2.47 GB
Measured Estimated VRAM 4 GB+
-
0.4B
ce-lery
japanese-mistral-300m-base
- F32 size
- 1.42 GB
- Memory at 8K
- -
Measured Estimated
-
12.2B
QuantFactory
Mistral-Nemo-Japanese-Instruct-2408
- Q4_K_M size
- 7.48 GB
- Memory at 8K
- 9.62 GB
Measured Estimated VRAM 12 GB+
-
1.8B
mmnga
line-corp-japanese-large-lm-1.7b-instruction-sft
- Q4_K_M size
- 1.15 GB
- Memory at 8K
- -
Measured Estimated
-
3.1B
sabaridsnfuji
Japanese-Receipt-VL-3B-JSON-v2
- Q4_K_M size
- 1.93 GB
- Memory at 8K
- 3.08 GB
Measured Estimated VRAM 4 GB+
-
20.9B
JMingo
gemma-4-26B-A4B-it-qat-japanese-pruned
- Q4_0 size
- 4.58 GB
- Memory at 8K
- 6.14 GB
Measured Estimated VRAM 6 GB+
-
34.7B
Aratako
Drama-3-Japanese
- Q4_K_M size
- 21.2 GB
- Memory at 8K
- 22.5 GB
Measured Estimated VRAM 24 GB+
-
30.5B
NandemoGHS
Anime-Speech-Japanese-Refiner
- Q4_K_M size
- 18.6 GB
- Memory at 8K
- 20.2 GB
Measured Estimated VRAM 24 GB+
-
6.7B
RichardErkhov
elyza_-_ELYZA-japanese-CodeLlama-7b-instruct
- Q4_K_M size
- 4.08 GB
- Memory at 8K
- 8.98 GB
Measured Estimated VRAM 12 GB+
-
32.8B
dahara1
unsloth-QwQ-32B-gguf-japanese-imatrix
- Q4_K_M size
- 19.9 GB
- Memory at 8K
- 23.1 GB
Measured Estimated VRAM 24 GB+
-
8B
nk2t
Llama-3-8B-Instruct-japanese-nk2t-v0.2
- Q4_K_M size
- 4.92 GB
- Memory at 8K
- 6.79 GB
Measured Estimated VRAM 8 GB+
-
6.7B
QuantFactory
ELYZA-japanese-Llama-2-7b-instruct
- Q4_K_M size
- 4.08 GB
- Memory at 8K
- -
Measured Estimated
-
8B
QuantFactory
suzume-llama-3-8B-japanese
- Q4_K_M size
- 4.92 GB
- Memory at 8K
- 6.79 GB
Measured Estimated VRAM 8 GB+
-
1.9B
ago99
llm-jp-3.1-1.8b-v02b
- Q4_K_M size
- 1.16 GB
- Memory at 8K
- -
Measured Estimated
-
8B
RichardErkhov
haqishen_-_Llama-3-8B-Japanese-Instruct
- Q4_K_M size
- 4.92 GB
- Memory at 8K
- 6.79 GB
Measured Estimated VRAM 8 GB+
-
8B
mpasila
Llama-3.1-Swallow-JP-EN-Translator-v1-8B
- Q4_K_M size
- 4.92 GB
- Memory at 8K
- 6.79 GB
Measured Estimated VRAM 8 GB+
-
1.4B
mmnga
stockmark-gpt-neox-japanese-1.4b
- Q4_K_M size
- 0.92 GB
- Memory at 8K
- -
Measured Estimated
-
2.8B
stabilityai
japanese-stablelm-3b-4e1t-instruct
- Q4_K_M size
- 1.71 GB
- Memory at 8K
- -
Measured Estimated
-
2.8B
stabilityai
japanese-stablelm-3b-4e1t-base
- Q4_K_M size
- 1.71 GB
- Memory at 8K
- -
Measured Estimated
-
3.1B
dahara1
Qwen2.5-3B-Instruct-gguf-japanese-imatrix-128K
- Q4_K_M size
- 1.93 GB
- Memory at 8K
- 3.31 GB
Measured Estimated VRAM 4 GB+
-
14.8B
dahara1
DeepSeek-R1-Distill-Qwen-14B-unsloth-gguf-japanese-imatrix
- Q4_K_M size
- 8.99 GB
- Memory at 8K
- 11.7 GB
Measured Estimated VRAM 12 GB+
-
0.4B
sabaridsnfuji
Japanese-Receipt-VL-lfm2-450M
- Q4_K_M size
- 0.23 GB
- Memory at 8K
- 1.00 GB
Measured Estimated VRAM 4 GB+
-
2.8B
RichardErkhov
stabilityai_-_japanese-stablelm-3b-4e1t-instruct
- Q4_K_M size
- 1.71 GB
- Memory at 8K
- -
Measured Estimated
-
19.3B
JMingo
gemma-4-26B-A4B-it-Japanese-96e
- Q4_K_M size
- 13.1 GB
- Memory at 8K
- 14.7 GB
Measured Estimated VRAM 16 GB+
-
1.7B
hotchpotch
query-crafter-japanese-Qwen3-1.7B
- Q4_K_M size
- 1.11 GB
- Memory at 8K
- 2.89 GB
Measured Estimated VRAM 4 GB+
-
13.7B
mmnga
llm-jp-13b-instruct-full-ac_001_16x-dolly-ichikara_004_001_single-oasst-oasst2-v2.0
- Q4_K_M size
- 8.33 GB
- Memory at 8K
- -
Measured Estimated
-
32.1B
third-intelligence
llm-jp-4-kappa-32b-a3b-v0.1
- Q4_K_M size
- 21.4 GB
- Memory at 8K
- 22.9 GB
Measured Estimated VRAM 24 GB+
-
7.2B
MaziyarPanahi
japanese-stablelm-base-gamma-7b-Mistral-7B-Instruct-v0.1
- Q4_K_M size
- 4.37 GB
- Memory at 8K
- 6.04 GB
Measured Estimated VRAM 6 GB+
-
0.8B
Takenoko12345678
Qwen3.5-0.8B-Japanese-SFT
- Q4_K_M size
- 0.53 GB
- Memory at 8K
- 1.70 GB
Measured Estimated VRAM 4 GB+
-
7.2B
TFMC
Japanese-Starling-ChatV-7B
- Q4_K_M size
- 4.37 GB
- Memory at 8K
- -
Measured Estimated
-
1.5B
dahara1
Qwen2.5-1.5B-Instruct-gguf-japanese-imatrix-128K
- Q4_K_M size
- 0.99 GB
- Memory at 8K
- 2.29 GB
Measured Estimated VRAM 4 GB+
-
8.6B
tokinasin
llm-jp-4-8b-thinking-uncensored-ara
- Q4_K_M size
- 5.30 GB
- Memory at 8K
- 7.32 GB
Measured Estimated VRAM 8 GB+
-
6.9B
RichardErkhov
stabilityai_-_japanese-stablelm-instruct-ja_vocab-beta-7b
- Q4_K_M size
- 4.18 GB
- Memory at 8K
- -
Measured Estimated
-
7.2B
MaziyarPanahi
japanese-stablelm-instruct-gamma-7b-Mistral-7B-Instruct-v0.1
- Q4_K_M size
- 4.37 GB
- Memory at 8K
- 6.04 GB
Measured Estimated VRAM 6 GB+
-
6.7B
RichardErkhov
stabilityai_-_japanese-stablelm-base-beta-7b
- Q4_K_M size
- 4.08 GB
- Memory at 8K
- -
Measured Estimated
-
8B
haqishen
Llama-3-8B-Japanese-Instruct
- Q4_K_M size
- 4.92 GB
- Memory at 8K
- 6.79 GB
Measured Estimated VRAM 8 GB+
-
8.6B
tokinasin
llm-jp-4-vl-9b-GGUF-v0.1
- Q4_K_M size
- 5.30 GB
- Memory at 8K
- 7.32 GB
Measured Estimated VRAM 8 GB+
-
2.8B
RichardErkhov
stabilityai_-_japanese-stablelm-3b-4e1t-base
- Q4_K_M size
- 1.71 GB
- Memory at 8K
- -
Measured Estimated
-
13.7B
mmnga
llm-jp-13b-v2.0
- Q4_K_M size
- 8.33 GB
- Memory at 8K
- -
Measured Estimated
-
14.7B
dahara1
unsloth-phi-4-gguf-japanese-imatrix
- Q4_K_M size
- 8.89 GB
- Memory at 8K
- 11.3 GB
Measured Estimated VRAM 12 GB+
-
14.8B
dahara1
Qwen2.5-14B-Instruct-gguf-japanese-imatrix-128K
- Q4_K_M size
- 8.99 GB
- Memory at 8K
- 11.7 GB
Measured Estimated VRAM 12 GB+
-
4.6B
JMingo
gemma-4-E4B-it-heretic-japanese-only-UD
- Q4_K_M size
- 3.01 GB
- Memory at 8K
- 4.26 GB
Measured Estimated VRAM 4 GB+
-
70.6B
mmnga
Llama-3-70B-japanese-suzume-vector-v0.1
- Q4_K_M size
- 42.5 GB
- Memory at 8K
- 46.0 GB
Measured Estimated VRAM 48 GB+
-
2.8B
mmnga
japanese-stablelm-3b-4e1t-instruct
- Q4_K_M size
- 1.71 GB
- Memory at 8K
- -
Measured Estimated
-
0.6B
yakimask2
qwen3-0.6B-japanese-thinking
- Q4_K_M size
- 0.40 GB
- Memory at 8K
- 1.56 GB
Measured Estimated VRAM 4 GB+
-
6.7B
RichardErkhov
stabilityai_-_japanese-stablelm-instruct-beta-7b
- Q4_K_M size
- 4.08 GB
- Memory at 8K
- -
Measured Estimated
-
32.8B
deep-analysis-research
Flux-Japanese-Qwen2.5-32B-Instruct-V1.0
- Q4_K_M size
- 19.9 GB
- Memory at 8K
- 22.8 GB
Measured Estimated VRAM 24 GB+
-
6.9B
RichardErkhov
stabilityai_-_japanese-stablelm-base-ja_vocab-beta-7b
- Q4_K_M size
- 4.18 GB
- Memory at 8K
- -
Measured Estimated
-
8.2B
John1604
John1604-AI-status-japanese-2025
- Q4_K_M size
- 5.03 GB
- Memory at 8K
- 7.08 GB
Measured Estimated VRAM 8 GB+
-
7.2B
MaziyarPanahi
japanese-stablelm-base-gamma-7b-Mistral-7B-Instruct-v0.2-slerp
- Q4_K_M size
- 4.37 GB
- Memory at 8K
- 6.04 GB
Measured Estimated VRAM 6 GB+
-
22.2B
Saxo
Linkbricks-Horizon-AI-Japanese-Superb-V1-22B
- Q4_K_M size
- 13.3 GB
- Memory at 8K
- 15.8 GB
Measured Estimated VRAM 16 GB+
-
1.2B
UmbrellaInc
Japanese_Zombie-3.2-1B
- Q4_K_M size
- 0.81 GB
- Memory at 8K
- 1.88 GB
Measured Estimated VRAM 4 GB+
-
7.2B
RichardErkhov
TFMC_-_Japanese-Starling-ChatV-7B
- Q4_K_M size
- 4.37 GB
- Memory at 8K
- -
Measured Estimated
-
3.8B
AXCXEPT
llm-jp-3-3.7b-instruct-EZO-Humanities
- Q4_K_M size
- 2.33 GB
- Memory at 8K
- -
Measured Estimated
-
3.8B
AXCXEPT
llm-jp-3-3.7b-instruct-EZO-Common
- Q4_K_M size
- 2.33 GB
- Memory at 8K
- -
Measured Estimated
-
1.5B
KMasaki
llm-jp-3-3.7b-Open-R1-Distill
- Q4_K_M size
- 0.99 GB
- Memory at 8K
- 2.29 GB
Measured Estimated VRAM 4 GB+
-
26.2B
aixsatoshi
llm-jp-1.8bx24-combined
- Q4_K_M size
- 15.9 GB
- Memory at 8K
- -
Measured Estimated
-
3.6B
mmnga
rinna-japanese-gpt-neox-3.6b-instruction-ppo
- Q4_0 size
- 2.06 GB
- Memory at 8K
- -
Measured Estimated
-
6.7B
Nisk36
FT_elyza_ELYZA-japanese-Llama-2-7b-instruct
- Q4_K_M size
- 4.08 GB
- Memory at 8K
- -
Measured Estimated
-
8B
nappa0326
llama-3-elyza-jp-8b-ft-functioncalling
- Q4_K_M size
- 4.92 GB
- Memory at 8K
- 6.79 GB
Measured Estimated VRAM 8 GB+
-
13.7B
mmnga
llm-jp-13b-instruct-full-ac_001-dolly-ichikara_004_001_single-oasst-oasst2-v2.0
- Q4_K_M size
- 8.33 GB
- Memory at 8K
- -
Measured Estimated
-
8B
RichardErkhov
hiroki-rad_-_elyza-Llama-3-ELYZA-JP-8B-512-aug-ft-rad-consult-mod
- Q4_K_M size
- 4.92 GB
- Memory at 8K
- 6.79 GB
Measured Estimated VRAM 8 GB+
-
8.6B
rinrin0413
llm-jp-4-8b-instruct-Q4_K_M
- Q4_K_M size
- 5.30 GB
- Memory at 8K
- 7.32 GB
Measured Estimated VRAM 8 GB+
-
11.2B
Aratako
ELYZA-japanese-Llama-2-fast-MoE-2x7B-v0.1
- Q4_K_M size
- 6.78 GB
- Memory at 8K
- -
Measured Estimated
-
3.6B
mmnga
rinna-japanese-gpt-neox-3.6b
- Q4_0 size
- 2.06 GB
- Memory at 8K
- -
Measured Estimated
-
1.4B
taoki
llm-jp-1.3b-v1.0-staircaptions-FT
- Q4_K_M size
- 0.92 GB
- Memory at 8K
- -
Measured Estimated
-
6.7B
RichardErkhov
Nisk36_-_finetuned-elyza_ELYZA-japanese-Llama-2-7b-instruct
- Q4_K_M size
- 4.08 GB
- Memory at 8K
- -
Measured Estimated
-
13.1B
mmnga
ELYZA-japanese-Llama-2-13b-fast
- Q4_K_M size
- 7.96 GB
- Memory at 8K
- -
Measured Estimated
-
13.7B
DataPilot
ArrowIdeative-13b-NeoBase-ZERO-llm-jp-v0.1
- Q4_K_M size
- 8.35 GB
- Memory at 8K
- -
Measured Estimated
-
6.8B
opparco
ELYZA-japanese-Llama-2-7b-fast
- Q4_K_M size
- 4.16 GB
- Memory at 8K
- -
Measured Estimated
-
6.8B
opparco
ELYZA-japanese-Llama-2-7b-fast-instruct
- Q4_K_M size
- 4.16 GB
- Memory at 8K
- -
Measured Estimated
-
13.1B
mmnga
llm-jp-13b-instruct-full-dolly-oasst-v1.0
- Q4_K_M size
- 8.39 GB
- Memory at 8K
- -
Measured Estimated
-
8.2B
SiliconJelly
shisa-v2.1-qwen3-8b-UD-japanese-imatrix
- Q4_K_M size
- 5.03 GB
- Memory at 8K
- 7.08 GB
Measured Estimated VRAM 8 GB+
-
8B
Nisk36
Llama-3-ELYZA-JP-8B-ojousama-chosen
- Q4_K_M size
- 4.92 GB
- Memory at 8K
- 6.79 GB
Measured Estimated VRAM 8 GB+
-
8B
keichankotaro
Llama-3-ELYZA-JP-8B-Optimize-KanColle-Verniy
- Q4_K_M size
- 4.92 GB
- Memory at 8K
- 6.79 GB
Measured Estimated VRAM 8 GB+
-
13.1B
mmnga
llm-jp-13b-v1.0
- Q4_K_M size
- 8.39 GB
- Memory at 8K
- -
Measured Estimated
-
21.5B
Aratako
ELYZA-japanese-Llama-2-MoE-2x13B-v0.1
- Q4_K_M size
- 13.0 GB
- Memory at 8K
- -
Measured Estimated
-
6.7B
77ko88ok
ELYZA-japanese-CodeLlama-7b-instruct
- Q4_K_M size
- 4.08 GB
- Memory at 8K
- 8.98 GB
Measured Estimated VRAM 12 GB+
-
8B
0017-alt
Llama-3-ELYZA-JP-8B-finetuned-1k
- Q4_K_M size
- 4.92 GB
- Memory at 8K
- 6.79 GB
Measured Estimated VRAM 8 GB+
-
11.1B
Aratako
ELYZA-japanese-Llama-2-MoE-2x7B-v0.1
- Q4_K_M size
- 6.70 GB
- Memory at 8K
- -
Measured Estimated
-
8B
Nisk36
Llama-3-ELYZA-JP-8B-normal-chosen
- Q4_K_M size
- 4.92 GB
- Memory at 8K
- 6.79 GB
Measured Estimated VRAM 8 GB+
-
6.7B
RichardErkhov
Nisk36_-_finetuned-._outputelyza_ELYZA-japanese-Llama-2-7b-instruct2024-12-05
- Q4_K_M size
- 4.08 GB
- Memory at 8K
- -
Measured Estimated
-
1.4B
mmnga
llm-jp-1.3b-v1.0
- Q4_K_M size
- 0.92 GB
- Memory at 8K
- -
Measured Estimated
-
13.7B
mmnga
llm-jp-13b-instruct-full-dolly-ichikara_004_001_single-oasst-oasst2-v2.0
- Q4_K_M size
- 8.33 GB
- Memory at 8K
- -
Measured Estimated
Multilingual models that list Japanese
The original model's Hugging Face page lists Japanese (ja) as a supported language. Japanese is one of many languages these models support.
-
7.5B
tencent
Hy-MT2-7B
- Q4_K_M size
- 4.62 GB
- Memory at 8K
- 6.50 GB
Measured Estimated VRAM 8 GB+
-
26.9B
DavidAU
Qwen3.8-27B-Turbo-Brilliance-50X-Reasoning-Instruct-NEO-MAX-MTP
- Q4_K_M size
- 16.5 GB
- Memory at 8K
- 18.3 GB
Measured Estimated VRAM 24 GB+
-
Jackrong
Qwopus3.8-27B-Flash-V2
- Q4_K_M size
- 16.8 GB
- Memory at 8K
- 18.5 GB
Measured Estimated VRAM 24 GB+
-
24B
DavidAU
LFM2.5-24B-A2B-Turbo-Brilliance-50X-NEO-MAX-Imatrix
- IQ3_M size
- 10.5 GB
- Memory at 8K
- 11.5 GB
Measured Estimated VRAM 12 GB+
-
24B
AtomicChat
LFM2.5-24B-A2B-Uncensored
- Q4_K_M size
- 15.4 GB
- Memory at 8K
- 16.3 GB
Measured Estimated VRAM 16 GB+
-
7.5B
nvidia
NVIDIA-Nemotron-3.5-Bolt-E4B
- UD-IQ2_M size
- 3.53 GB
- Memory at 8K
- 4.78 GB
Measured Estimated VRAM 6 GB+
-
176.9B
FINAL-Bench
POCKET-Darwin-180B
- UD-Q4_K_XL size
- 111 GB
- Memory at 8K
- 113 GB
Measured Estimated VRAM 128 GB+
-
34.7B
FINAL-Bench
POCKET-35B
- Q4_K_M size
- 21.2 GB
- Memory at 8K
- 22.4 GB
Measured Estimated VRAM 24 GB+
-
24B
LiquidAI
LFM2.5-24B-A2B
- UD-IQ2_XXS size
- 7.47 GB
- Memory at 8K
- 8.44 GB
Measured Estimated VRAM 8 GB+
-
27.3B
DavidAU
Qwen3.8-27B-Jumbo-Fusion-IQ-747-900-Turbo-Brilliance-50X-Reasoning-Instruct-NEO-MAX-MTP
- Q4_K_M size
- 16.8 GB
- Memory at 8K
- 18.6 GB
Measured Estimated VRAM 24 GB+
-
1.8B
tencent
Hy-MT2-1.8B
- Q4_K_M size
- 1.13 GB
- Memory at 8K
- 2.45 GB
Measured Estimated VRAM 4 GB+
-
9B
xtools-at
DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic
- Q4_K_M size
- 5.63 GB
- Memory at 8K
- 7.00 GB
Measured Estimated VRAM 8 GB+
-
8.8B
ibm-granite
granite-4.2-8b
- Q4_K_M size
- 5.35 GB
- Memory at 8K
- 7.43 GB
Measured Estimated VRAM 8 GB+
-
3.7B
ibm-granite
granite-4.2-3b
- Q4_K_M size
- 2.24 GB
- Memory at 8K
- 3.66 GB
Measured Estimated VRAM 4 GB+
-
1.2B
LiquidAI
LFM2.5-1.2B-Instruct
- Q4_K_M size
- 0.73 GB
- Memory at 8K
- 1.50 GB
Measured Estimated VRAM 4 GB+
-
29.3B
ibm-granite
granite-4.2-30b
- Q4_K_M size
- 17.7 GB
- Memory at 8K
- 20.6 GB
Measured Estimated VRAM 24 GB+
-
176.9B
DavidAU
Qwen3.8-Flash-Next-Turbo-Brilliance-50x-Reasoning-Instruct-GSQ-RCO
- IQ3_S size
- 83.6 GB
- Memory at 8K
- 85.0 GB
Measured Estimated VRAM 96 GB+
-
31.6B
nvidia
NVIDIA-Nemotron-3.5-Lightning-30B-A3B
- Q4_0 size
- 18.9 GB
- Memory at 8K
- 19.8 GB
Measured Estimated VRAM 24 GB+
-
0.4B
LiquidAI
LFM2.5-350M
- Q4_K_M size
- 0.23 GB
- Memory at 8K
- 1.00 GB
Measured Estimated VRAM 4 GB+
-
Jackrong
Qwopus3.6-35B-A3B-Coder-MTP
- Q4_K_M size
- 21.7 GB
- Memory at 8K
- 23.0 GB
Measured Estimated VRAM 24 GB+
-
9.2B
Jackrong
DeepSeek-V4-Pro-Qwen3.5-9B-MTP
- Q4_K_M size
- 5.78 GB
- Memory at 8K
- 7.15 GB
Measured Estimated VRAM 8 GB+
-
2.7B
LiquidAI
LFM2.5-2.6B
- Q4_K_M size
- 1.67 GB
- Memory at 8K
- 2.61 GB
Measured Estimated VRAM 4 GB+
-
176.9B
DavidAU
Qwen3.8-Flash-Next-Abliterated-Uncensored-Turbo-Brilliance-50x-Reasoning-Instruct-GSQ-RCO
- IQ3_S size
- 83.9 GB
- Memory at 8K
- 85.3 GB
Measured Estimated VRAM 96 GB+
-
3.7B
taronaeo
Granite-4.2-3B-BE
- Q4_K_M size
- 2.24 GB
- Memory at 8K
- 3.66 GB
Measured Estimated VRAM 4 GB+
The grouping uses only facts: the developer's account, the model name and the languages listed on the model page. Actual Japanese output quality depends on the model and use.