BenchClub
Home
Challenges
Leaderboard
Search models
Studio
Sign in
Formats
Quantized builds on Hugging Face by file format, counted Nov 19, 2026.
By size
Labs
Releases
Families
Licenses
Most built on
Formats
All models
GGUF
9,700 builds
154
models
llama.cpp, Ollama, LM Studio
MLX
2,615 builds
117
models
Apple silicon: mlx-lm, LM Studio
AWQ
437 builds
95
models
vLLM, SGLang
GPTQ
675 builds
98
models
vLLM, SGLang
All sizes
≤3B
3–9B
9–20B
20–40B
40–80B
80–300B
>300B
Top build from
Anyone
unsloth
33
bartowski
25
mradermacher
16
TheBloke
14
Qwen
10
MaziyarPanahi
7
ibm-granite
5
second-state
5
ggml-org
#
Model
Size
Score
GGUF
MLX
AWQ
GPTQ
Most downloaded GGUF
1
G
gemma-3-1b-it
Google
1.0B
—
179
27
2
1
gemma-3-1b-it-GGUF
ggml-org · 541.7K downloads
2
N
NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16
NVIDIA
32.9B
1329
47
54
—
4
NVIDIA-Nemotron-3.5-Lightning-30B-A3B-GGUF
ggml-org · 217.3K downloads
3
G
GLM-4.6V
Z.ai
108B
1377
10
3
—
—
GLM-4.6V-GGUF
ggml-org · 34.7K downloads