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
Qwen3-8B
Qwen
8.2B
—
268
39
29
30
Qwen3-8B-GPTQ-Int4
JunHowie · 945 downloads
2
Q
Qwen3-32B
Qwen
32.8B
1340
57
14
16
13
Qwen3-32B-GPTQ-Int4
JunHowie · 823 downloads
3
Q
Qwen3-30B-A3B-Instruct-2507
Qwen
30.5B
1384
59
23
2
12
Qwen3-30B-A3B-Instruct-2507-GPTQ-Int4
JunHowie · 642 downloads
4
Q
Qwen3-4B-Instruct-2507
Qwen
4.0B
—
242
40
7
11
Qwen3-4B-Instruct-2507-GPTQ-Int8
JunHowie · 2.6K downloads
5
Q
Qwen3-4B
Qwen
4.0B
—
207
30
8
10
Qwen3-4B-GPTQ-Int4
JunHowie · 235 downloads
6
Q
Qwen3-14B
Qwen
14.8B
—
118
17
16
9
Qwen3-14B-GPTQ-Int4
JunHowie · 2.7K downloads