GGUF models by ggml-org

224 GGUF models quantized by ggml-org on Hugging Face. Sizes run from 1M to 1050B parameters. The longest trained context is 10240K tokens.

Most downloadedNewestLargestLongest contextSmallest
QW
Qwen3.8-27B
Qwen · ggml-org
Params3B
Context256K
Q4_K_M19.0 GB
Vision
MO
models moved
Models · ggml-org
Params34M
Context—
Smallest0.0 GB
GGUF
EM
Embeddinggemma 300m
Embeddinggemma · ggml-org
Params308M
Context2K
Smallest0.3 GB
Embedding
GE
gemma-4-26B-A4B-it
Gemma · ggml-org
Params450M
Context256K
Smallest0.3 GB
Vision
GP
gpt-oss-20b
gpt-oss · ggml-org
Params870M
Context128K
Smallest0.9 GB
GGUF
GE
Gemma 3 1b It
Gemma · ggml-org
Params1B
Context32K
Q4_K_M0.8 GB
GGUF
GP
gpt-oss-120b
gpt-oss · ggml-org
Params800M
Context128K
Smallest0.8 GB
GGUF
NE
NVIDIA-Nemotron-3.5-Lightning-30B-A3B
Nemotron · ggml-org
Params31.6B
Context1024K
Smallest1.2 GB
GGUF
GE
gemma-4-E2B-it
Gemma · ggml-org
Params4.65B
Context128K
Smallest0.1 GB
Vision
GE
gemma-4-E4B-it
Gemma · ggml-org
Params7.5B
Context128K
Smallest0.1 GB
Vision
QW
Qwen2.5 Omni 7B
Qwen · ggml-org
Params7.6B
Context32K
Q4_K_M4.7 GB
Vision
QW
Qwen3.6-35B-A3B
Qwen · ggml-org
Params1.9B
Context256K
Q4_K_M20.4 GB
Vision
QW
Qwen3 1.7B
Qwen · ggml-org
Params2.03B
Context40K
Q4_K_M1.3 GB
GGUF
QW
Qwen2.5 VL 3B Instruct
Qwen · ggml-org
Params3.09B
Context125K
Q4_K_M1.9 GB
Vision
QW
Qwen3 Reranker 0.6B
Qwen · ggml-org
Params596M
Context40K
Smallest0.6 GB
Embedding
TE
test model router download
Test · ggml-org
Params1M
Context2K
Smallest0.0 GB
GGUF
EM
embeddinggemma-2
Embeddinggemma · ggml-org
Params271M
Context256K
Smallest0.3 GB
EmbeddingVision
QW
Qwen2.5 Omni 3B
Qwen · ggml-org
Params3.4B
Context32K
Q4_K_M2.1 GB
Vision
QW
Qwen3.6-27B
Qwen · ggml-org
Params26.9B
Context256K
Q4_K_M19.1 GB
Vision
GE
Gemma 3 4b It
Gemma · ggml-org
Params3.88B
Context128K
Q4_K_M2.5 GB
Vision
CL
Clef-Flash
Clef · ggml-org
Params9.08B
Context256K
Q4_K_M6.7 GB
ReasoningTool useVision
GE
gemma-4-12B-it
Gemma · ggml-org
Params11.9B
Context256K
Smallest0.3 GB
ReasoningTool useVision
QW
Qwen2.5 VL 7B Instruct
Qwen · ggml-org
Params7.62B
Context125K
Q4_K_M4.7 GB
Vision
TI
tinygemma3
Tinygemma · ggml-org
Params38M
Context128K
Smallest0.0 GB
Vision
QW
Qwen3.8-Flash-Next
Qwen · ggml-org
Params177B
Context256K
Smallest0.4 GB
Vision
QW
Qwen3 Omni 30B A3B Instruct
Qwen · ggml-org
Params30.5B
Context64K
Q4_K_M18.6 GB
Vision
ST
stories15M MOE
Stories · ggml-org
Params8M
Context256
Smallest0.0 GB
GGUF
QW
Qwen3.5 0.8B
Qwen · ggml-org
Params773M
Context256K
Smallest0.6 GB
Vision
KE
Kev 4B
Kev · ggml-org
Params4.2B
Context256K
Q4_K_M3.0 GB
GGUF
NE
NVIDIA-Nemotron-3.5-Super-VL-120B-A12B
Nemotron · ggml-org
Params1.66B
Context1024K
Smallest1.4 GB
ReasoningTool useVision

About ggml-org on Hugging Face

ggml-org has published 224 GGUF models that ggufmodels.com tracks, across families such as Qwen, Gemma and Mistral. The most downloaded are Qwen3.8-27B, models moved and Embeddinggemma 300m.

The quants ggml-org publishes most often are Q8_0 (175), BF16 (75), Q4_K_M (69) and F16 (63). Their Q4_K_M files range from 0.1 to 169.9 GB. Parameter counts run from 1M to 1050B, and the longest trained context window is 10240K tokens.

Frequently asked questions

What GGUF models has ggml-org published?

224 models are listed here, mainly from the Qwen, Gemma and Mistral families. The most downloaded is Qwen3.8-27B.

Which quants does ggml-org publish?

The most common are Q8_0 (175 models), BF16 (75 models), Q4_K_M (69 models) and F16 (63 models).

Keep browsing