Download ranking
Most-downloaded local LLMs that run in 12 GB of VRAM
Only models with a quantization whose estimated memory fits in 12 GB at an 8,192-token context, in the same order. The quantization shown is the largest (most precise) one that fits.
Top 50 of 580 models
Rank changes are compared with the record from Nov 4, 2026.
-
1 no changeQwen3.8-27B
Qwen 27.3B
Downloads (30 days) 10,491,667
Likes 6,515
IQ2_S 12.9 GB
-
2 no changeOrnith-1.5-9B
ornith-ai 9.2B
Downloads (30 days) 5,801,033
Likes 743
Q8_0 11.2 GB
-
3 no changeOrnith-1.5-35B-A3B
ornith-ai 35.5B
Downloads (30 days) 4,267,948
Likes 721
IQ2_S 12.8 GB
-
4 no changeHuihui-Qwen3.8-27B-abliterated
huihui-ai 27.3B
Downloads (30 days) 3,958,526
Likes 1,907
UD-IQ3_XXS 12.8 GB
-
5 2up 2gemma-4-12B-it
google 11.9B
Downloads (30 days) 2,834,643
Likes 1,158
UD-Q6_K_XL 12.4 GB
-
6 no changeQwen3.5-9B
Qwen 9B
Downloads (30 days) 2,657,097
Likes 1,270
Q8_0 11.2 GB
-
7 2down 2Qwen3.8-27B-Uncensored
JonathanColetti 27.3B
Downloads (30 days) 2,472,728
Likes 1,964
IQ2_M 12.4 GB
-
8 2up 2MOSS-Music-8B-Instruct
OpenMOSS-Team
Downloads (30 days) 2,446,681
Likes 11
Q8_0 10.8 GB
-
9 2up 2gemma-4-26B-A4B-it
google 25.2B
Downloads (30 days) 2,434,395
Likes 1,579
UD-IQ3_S 12.8 GB
-
10 2down 2Ornith-1.0-9B
ornith-ai 9B
Downloads (30 days) 2,374,819
Likes 699
Q8_0 10.9 GB
-
11 2up 2Qwen3.6-35B-A3B
Qwen 34.7B
Downloads (30 days) 2,265,195
Likes 2,020
UD-IQ2_M 12.8 GB
-
12 2up 2Qwen3-VL-8B-Instruct
Qwen 8.2B
Downloads (30 days) 2,195,718
Likes 323
UD-Q8_K_XL 12.9 GB
-
13 5up 5Qwen3.6-35B-A3B-MTP
unsloth 35.5B
Downloads (30 days) 2,170,348
Likes 1,046
UD-IQ1_M 12.6 GB
-
14 2down 2
Downloads (30 days) 2,097,725
Likes 1,514
Q8_0 12.1 GB
-
15 6down 6
Downloads (30 days) 1,997,118
Likes 2,363
Q2_K 12.4 GB
-
16 no changeQwen3.5-4B
Qwen 4.2B
Downloads (30 days) 1,980,253
Likes 673
BF16 10.0 GB
-
17 no changeOrnith-1.5-9B-uncensored
junafinity 9B
Downloads (30 days) 1,736,789
Likes 278
Q8_0 10.9 GB
-
18 3down 3Ternary-Bonsai-2-27B
prism-ml 26.9B
Downloads (30 days) 1,620,572
Likes 2,982
Q2_0 9.37 GB
-
19 no changeSwift-1.5-Qwen3.8-27B-GSQ-RCO
ukisai 26.9B
Downloads (30 days) 1,607,683
Likes 508
IQ3_XXS 12.2 GB
-
20 1up 1gemma-4-E4B-it
google 7.5B
Downloads (30 days) 1,525,316
Likes 948
UD-Q8_K_XL 9.96 GB
-
21 1down 1Dirk-Qwen3.8-27B
peculiar-ragdoll 27.3B
Downloads (30 days) 1,400,070
Likes 265
IQ3_XXS 12.2 GB
-
22 2up 2Wan2.1
DeepBeepMeep
Downloads (30 days) 1,397,059
Likes 73
IQ2_M 12.4 GB
-
23 1down 1Qwen3.8-27B-GSQ-RCO
ISTA-DASLab 26.9B
Downloads (30 days) 1,364,705
Likes 2,618
IQ3_XXS 12.2 GB
-
24 1down 1Qwen3-4B
Qwen 4B
Downloads (30 days) 1,320,091
Likes 505
BF16 10.1 GB
-
25 no changegemma-4-E4B-it-qat-q4_0
google 7.5B
Downloads (30 days) 1,297,573
Likes 186
Q4_0 6.40 GB
-
26 21up 21Ternary-Bonsai-2-9B
prism-ml
Downloads (30 days) 1,219,968
Likes 163
Q8_0 4.04 GB
-
27 1down 1HyperCLOVAX-SEED-Text-Instruct-1.5B-Q4_K_M
rippertnt 1.8B
Downloads (30 days) 1,164,155
Likes 17
Q4_K_M 2.70 GB
-
28 3up 3gemma-4-12B-it-qat-q4_0
google 11.9B
Downloads (30 days) 1,164,140
Likes 396
Q4_0 8.69 GB
-
29 no changeHy-MT2-7B
tencent 7.5B
Downloads (30 days) 1,149,223
Likes 103
Q8_0 9.86 GB
-
30 10up 10Swift-1.5-Qwen3.8-27B-heretic-GSQ-RCO
jegreene 27.3B
Downloads (30 days) 1,142,899
Likes 33
IQ3_XXS 12.2 GB
-
31 4down 4Qwen3.8-27B-Heretic-Abliterated-Uncensored
0bserverx 26.9B
Downloads (30 days) 1,135,253
Likes 869
Q2_K 12.5 GB
-
32 4down 4Qwen3-VL-4B-Instruct
Qwen 4B
Downloads (30 days) 1,131,643
Likes 171
BF16 10.1 GB
-
33 3down 3Muse-Glimmer-30B
meta-models 27.9B
Downloads (30 days) 1,123,221
Likes 981
IQ3_XXS 12.7 GB
-
34 1down 1gemma-4-E2B-it
google 4.6B
Downloads (30 days) 1,114,000
Likes 513
BF16 10.4 GB
-
35 3down 3gpt-oss-20b
openai 20.9B
Downloads (30 days) 1,103,373
Likes 1,192
Q5_K_S 12.9 GB
-
36 2down 2Qwen3-8B
Qwen 8.2B
Downloads (30 days) 1,085,620
Likes 594
UD-Q8_K_XL 12.9 GB
-
37 20up 20Ternary-Bonsai-2-2B
prism-ml 1.9B
Downloads (30 days) 1,049,409
Likes 53
Q2_0 1.71 GB
-
38 5up 5
Downloads (30 days) 1,036,784
Likes 294
IQ3_XXS 12.2 GB
-
39 3down 3Qwen2.5-7B-Instruct
Qwen 7.6B
Downloads (30 days) 1,034,284
Likes 298
Q8_0 9.42 GB
-
40 5up 5Simplicio-27B
wesleysimplicio 27.3B
Downloads (30 days) 1,008,768
Likes 3
Q2_K 12.6 GB
-
41 3up 3Qwen3-4B-Instruct-2507
Qwen 4B
Downloads (30 days) 980,817
Likes 273
F16 10.1 GB
-
42 7down 7MiMo-V2.6-Distill-Qwen-9B
XiaomiMiMo 9B
Downloads (30 days) 980,287
Likes 191
Q8_0 10.9 GB
-
43 4down 4Qwen3.8-27B-AP
agentionai 27.3B
Downloads (30 days) 922,480
Likes 102
IQ3_XXS 12.5 GB
-
44 7down 7Qwopus3.8-27B-Flash-V2
Jackrong
Downloads (30 days) 911,719
Likes 74
Q2_K 12.6 GB
-
45 10up 10
Downloads (30 days) 911,661
Likes 59
IQ3_M 11.5 GB
-
46 8down 8Cyber-Ornith-1.5-9B-OBLITERATED
DuoNeural 9B
Downloads (30 days) 906,575
Likes 67
Q6_K 8.73 GB
-
47 6down 6Sharp-Spark-X2.5-4B
peculiar-ragdoll 4.1B
Downloads (30 days) 873,990
Likes 163
Q6_K_XL 4.83 GB
-
48 5up 5Qwen3.8-27B-Fable-5-Coding-Distilled
khazarai 27.3B
Downloads (30 days) 871,504
Likes 34
Q2_K 12.6 GB
-
49 1up 1AdaVaR-3B
ZejunLi 3.1B
Downloads (30 days) 858,206
Likes 3
F16 7.33 GB
-
50 10up 10Qwen3.5-9B-Kimi-k3-Distilled
khazarai 9.2B
Downloads (30 days) 800,999
Likes 21
Q8_0 11.2 GB
Estimated Memory at 8K: Estimated with a formula. Actual usage depends on your setup and settings.
About this ranking
- We count the download numbers (last 30 days) that Hugging Face publishes for each repository. When several sources publish the same model, we add up the sources we list.
- Only models that generate text (Hugging Face task such as "text generation" or "image-text-to-text") are ranked. Embedding, object detection, speech recognition and similar models are not included.
- Only sources whose numbers were refreshed from Hugging Face within the last 2 days are added (sources that dropped out of the top of the list, whose numbers are stale, are not counted).
- This ranks how much models are used, not their performance or quality. This site does not assign its own performance scores.
- Hugging Face counts every request to a GGUF file (including HEAD) as a download. A split file may be counted once per part for a single download.
- Downloads that do not go through Hugging Face, such as pulls from the official Ollama library (ollama.com), are not included.
Source: Hugging Face Hub API (fetched daily around 04:20 JST)