Download ranking

Most-downloaded local LLMs that run in 8 GB of VRAM

Only models with a quantization whose estimated memory fits in 8 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 453 models

Rank changes are compared with the record from Nov 4, 2026.

Rank Model Downloads (30 days) Likes Quantization that fits 8 GB
1 no change

Qwen3.8-27B
Qwen 27.3B

Downloads (30 days) 10,491,667

Likes 6,515

UD-IQ1_M 8.47 GB
2 no change

Ornith-1.5-9B
ornith-ai 9.2B

Downloads (30 days) 5,801,033

Likes 743

Q5_K_M 8.22 GB
3 1up 1

gemma-4-12B-it
google 11.9B

Downloads (30 days) 2,834,643

Likes 1,158

IQ4_XS 8.49 GB
4 1down 1

Qwen3.5-9B
Qwen 9B

Downloads (30 days) 2,657,097

Likes 1,270

Q5_K_M 8.48 GB
5 1up 1

MOSS-Music-8B-Instruct
OpenMOSS-Team

Downloads (30 days) 2,446,681

Likes 11

Q4_K_M 7.24 GB
6 1down 1

Ornith-1.0-9B
ornith-ai 9B

Downloads (30 days) 2,374,819

Likes 699

Q5_K_M 7.86 GB
7 1up 1

Qwen3-VL-8B-Instruct
Qwen 8.2B

Downloads (30 days) 2,195,718

Likes 323

UD-Q5_K_XL 7.94 GB
8 1down 1

Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP
DavidAU 9B

Downloads (30 days) 2,097,725

Likes 1,514

Q4_K_M 8.35 GB
9 no change

Qwen3.5-4B
Qwen 4.2B

Downloads (30 days) 1,980,253

Likes 673

UD-Q8_K_XL 7.32 GB
10 no change

Ornith-1.5-9B-uncensored
junafinity 9B

Downloads (30 days) 1,736,789

Likes 278

Q5_K_M 7.83 GB
11 no change

gemma-4-E4B-it
google 7.5B

Downloads (30 days) 1,525,316

Likes 948

Q6_K_L 8.43 GB
12 1up 1

Wan2.1
DeepBeepMeep

Downloads (30 days) 1,397,059

Likes 73

Q4_K_M 7.55 GB
13 1down 1

Qwen3-4B
Qwen 4B

Downloads (30 days) 1,320,091

Likes 505

UD-Q8_K_XL 7.11 GB
14 no change

gemma-4-E4B-it-qat-q4_0
google 7.5B

Downloads (30 days) 1,297,573

Likes 186

Q4_0 6.40 GB
15 12up 12

Ternary-Bonsai-2-9B
prism-ml

Downloads (30 days) 1,219,968

Likes 163

Q8_0 4.04 GB
16 1down 1

HyperCLOVAX-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
17 no change

Hy-MT2-7B
tencent 7.5B

Downloads (30 days) 1,149,223

Likes 103

Q6_K 8.04 GB
18 2down 2

Qwen3-VL-4B-Instruct
Qwen 4B

Downloads (30 days) 1,131,643

Likes 171

UD-Q8_K_XL 7.11 GB
19 1down 1

Muse-Glimmer-30B
meta-models 27.9B

Downloads (30 days) 1,123,221

Likes 981

IQ1_M 8.22 GB
20 1down 1

gemma-4-E2B-it
google 4.6B

Downloads (30 days) 1,114,000

Likes 513

UD-Q8_K_XL 6.42 GB
21 1down 1

Qwen3-8B
Qwen 8.2B

Downloads (30 days) 1,085,620

Likes 594

Q5_K_L 8.29 GB
22 11up 11

Ternary-Bonsai-2-2B
prism-ml 1.9B

Downloads (30 days) 1,049,409

Likes 53

Q2_0 1.71 GB
23 1down 1

Qwen2.5-7B-Instruct
Qwen 7.6B

Downloads (30 days) 1,034,284

Likes 298

Q6_K_L 7.84 GB
24 1up 1

Qwen3-4B-Instruct-2507
Qwen 4B

Downloads (30 days) 980,817

Likes 273

UD-Q8_K_XL 7.11 GB
25 4down 4

MiMo-V2.6-Distill-Qwen-9B
XiaomiMiMo 9B

Downloads (30 days) 980,287

Likes 191

Q5_K_M 8.24 GB
26 3down 3

Cyber-Ornith-1.5-9B-OBLITERATED
DuoNeural 9B

Downloads (30 days) 906,575

Likes 67

Q5_K_M 7.83 GB
27 3down 3

Sharp-Spark-X2.5-4B
peculiar-ragdoll 4.1B

Downloads (30 days) 873,990

Likes 163

Q6_K_XL 4.83 GB
28 1up 1

AdaVaR-3B
ZejunLi 3.1B

Downloads (30 days) 858,206

Likes 3

F16 7.33 GB
29 6up 6

Qwen3.5-9B-Kimi-k3-Distilled
khazarai 9.2B

Downloads (30 days) 800,999

Likes 21

Q5_K_M 8.01 GB
30 7up 7

B1-9B
schneewolflabs 9.2B

Downloads (30 days) 752,708

Likes 0

Q5_K_M 8.01 GB
31 10up 10

LFM2.5-24B-A2B
LiquidAI 24B

Downloads (30 days) 722,280

Likes 379

UD-IQ2_M 8.50 GB
32 26up 26

Diplodocus-preview
OsaurusAI 9B

Downloads (30 days) 699,889

Likes 1

Q4_K_M 8.59 GB
33 7up 7

gemma-3-1b-it
google 1B

Downloads (30 days) 692,076

Likes 164

F16 3.14 GB
34 2down 2

Qwen3-0.6B
Qwen 0.6B

Downloads (30 days) 673,305

Likes 321

BF16 3.30 GB
35 5down 5

Spark-X2.5-4B
XHToken 4.1B

Downloads (30 days) 648,808

Likes 316

Q8_0 5.60 GB
36 20up 20

Spark-X2.6-4B
XHToken 4.4B

Downloads (30 days) 632,009

Likes 304

Q8_0 5.60 GB
37 6down 6

Qwen3.5-9B-Uncensored-HauhauCS-Aggressive
HauhauCS 9B

Downloads (30 days) 624,698

Likes 2,489

Q4_K_M 6.99 GB
38 12down 12

Gemma-4-E4B-Uncensored-HauhauCS-Aggressive
HauhauCS 7.5B

Downloads (30 days) 622,519

Likes 1,567

Q6_K 7.50 GB
39 1down 1

Qwen3.5-2B
Qwen 1.9B

Downloads (30 days) 610,814

Likes 216

BF16 5.06 GB
40 12down 12

Qwen3-VL-8B-Instruct-abliterated
mradermacher 8.2B

Downloads (30 days) 596,686

Likes 24

Q5_K_M 8.13 GB
41 5down 5

Qwen3.8-4B-Distill
empero-ai 4.3B

Downloads (30 days) 575,679

Likes 206

Q8_0 5.98 GB
42 8down 8

Qwen3-1.7B
Qwen 1.7B

Downloads (30 days) 575,386

Likes 222

BF16 5.86 GB
43 6up 6

Qwen2.5-VL-7B-Instruct
Qwen 7.6B

Downloads (30 days) 575,300

Likes 288

UD-Q6_K_XL 8.28 GB
44 9up 9

Spark-X2.5-4B-Heretic-jp
soyaakinohara 4.1B

Downloads (30 days) 574,549

Likes 22

Q8_0 5.60 GB
45 3down 3

Qwen2.5-1.5B-Instruct
Qwen 1.8B

Downloads (30 days) 572,604

Likes 222

F16 4.64 GB
46 new

DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic
xtools-at 9B

Downloads (30 days) 564,433

Likes 301

Q5_K_M 7.83 GB
47 3down 3

Qwen3-14B
Qwen 14.8B

Downloads (30 days) 545,651

Likes 327

IQ3_XS 8.57 GB
48 9down 9

Qwen3.8-9B-Distill
empero-ai 9.2B

Downloads (30 days) 538,842

Likes 350

Q5_K_M 8.01 GB
49 6down 6

Qwen2.5-0.5B-Instruct
Qwen 0.6B

Downloads (30 days) 532,787

Likes 188

F16 2.22 GB
50 5down 5

Qwen3.8-2B-Distill
empero-ai 1.9B

Downloads (30 days) 510,870

Likes 182

BF16 5.06 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)