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
G
gemma-4-31B-it
Google
31.3B
1443
152
65
7
7
google_gemma-4-31B-it-ingest-best-gptq
positron-ai · 683 downloads
2
G
gemma-4-26B-A4B-it
Google
25.8B
1434
216
88
9
6
google_gemma-4-26B-A4B-it-ingest-best-gptq
positron-ai · 695 downloads
3
G
gemma-3-27b-it
Google
27.4B
1358
92
5
4
3
google_gemma-3-27b-it-ingest-best-gptq
positron-ai · 960 downloads
4
G
gpt-oss-20b
OpenAI
20.9B
1288
101
64
—
1
openai_gpt-oss-20b-ingest-best-gptq
positron-ai · 43 downloads
5
G
gpt-oss-120b
OpenAI
117B
1366
49
41
—
1
openai_gpt-oss-120b-ingest-best-gptq
positron-ai · 48 downloads