BenchClub
Home
Challenges
Leaderboard
Search models
Studio
Sign in
Formats
Quantized builds on Hugging Face by file format, counted Nov 18, 2026.
By size
Labs
Releases
Families
Licenses
Most built on
Formats
All models
GGUF
12,112 builds
233
models
llama.cpp, Ollama, LM Studio
MLX
3,437 builds
188
models
Apple silicon: mlx-lm, LM Studio
AWQ
574 builds
129
models
vLLM, SGLang
GPTQ
821 builds
130
models
vLLM, SGLang
All sizes
≤3B
3–9B
9–20B
20–40B
40–80B
80–300B
>300B
Top build from
Anyone
Qwen
16
TheBloke
16
fbaldassarri
7
JunHowie
6
QuantTrio
5
positron-ai
5
ModelCloud
5
RedHatAI
3
#
Model
Size
Score
GGUF
MLX
AWQ
GPTQ
Most downloaded GPTQ
1
Q
Qwen3-1.7B
Qwen
2.0B
—
258
40
11
19
Qwen3-1.7B-GPTQ-Int8
Qwen · 1.1K downloads
2
Q
Qwen2.5-1.5B-Instruct
Qwen
1.5B
—
239
31
9
14
Qwen2.5-1.5B-Instruct-GPTQ-Int4
Qwen · 2K downloads
3
Q
Qwen3-0.6B
Qwen
752M
—
331
50
4
13
Qwen3-0.6B-GPTQ-Int8
Qwen · 1K downloads
4
Q
Qwen3.5-35B-A3B
Qwen
36.0B
1395
176
62
10
12
Qwen3.5-35B-A3B-GPTQ-Int4
Qwen · 322.7K downloads
5
Q
Qwen2.5-72B-Instruct
Qwen
72.7B
1269
22
5
5
11
Qwen2.5-72B-Instruct-GPTQ-Int4
Qwen · 6.7K downloads
6
Q
Qwen2.5-7B-Instruct
Qwen
7.6B
—
276
47
15
8
Qwen2.5-7B-Instruct-GPTQ-Int4
Qwen · 17.8K downloads
7
Q
Qwen2.5-0.5B-Instruct
Qwen
494M
—
239
31
8
7
Qwen2.5-0.5B-Instruct-GPTQ-Int4
Qwen · 2.6K downloads
8
Q
Qwen2.5-3B-Instruct
Qwen
3.1B
—
250
37
5
7
Qwen2.5-3B-Instruct-GPTQ-Int4
Qwen · 2K downloads
9
Q
Qwen2.5-Coder-32B-Instruct
Qwen
32.8B
1230
71
23
4
6
Qwen2.5-Coder-32B-Instruct-GPTQ-Int8
Qwen · 30.5K downloads
10
Q
Qwen3-30B-A3B
Qwen
30.5B
1317
57
16
6
4
Qwen3-30B-A3B-GPTQ-Int4
Qwen · 18.5K downloads
11
Q
Qwen3-235B-A22B
Qwen
235B
1394
16
8
1
4
Qwen3-235B-A22B-GPTQ-Int4
Qwen · 1.5K downloads
12
Q
Qwen2.5-Coder-14B-Instruct
Qwen
14.8B
—
88
21
3
3
Qwen2.5-Coder-14B-Instruct-GPTQ-Int4
Qwen · 4.7K downloads
13
Q
Qwen2.5-32B-Instruct
Qwen
32.8B
—
68
9
7
3
Qwen2.5-32B-Instruct-GPTQ-Int4
Qwen · 380.4K downloads
14
Q
Qwen2-72B-Instruct
Qwen
72.7B
1203
13
—
1
3
Qwen2-72B-Instruct-GPTQ-Int4
Qwen · 338 downloads
15
Q
Qwen2.5-Coder-7B-Instruct
Qwen
7.6B
—
207
31
5
2
Qwen2.5-Coder-7B-Instruct-GPTQ-Int4
Qwen · 432.7K downloads
16
Q
Qwen3.5-397B-A17B
Qwen
403B
1438
22
23
2
2
Qwen3.5-397B-A17B-GPTQ-Int4
Qwen · 5.2K downloads