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.
IN
InternVL2_5 1B
Internvl · ggml-org
Params630M
Context32K
Smallest0.7 GB
LL
Llama-4-Scout-17B-16E-Instruct
Llama · ggml-org
Params108B
Context10240K
Q4_K_M65.4 GB
GE
gemma-4-26B-A4B
Gemma · ggml-org
Params25.2B
Context256K
Smallest26.9 GB
GE
gemma-4-E4B
Gemma · ggml-org
Params7.52B
Context128K
Smallest8.0 GB
LL
Llama-2-7B
Llama · ggml-org
Params6.74B
Context4K
Smallest3.8 GB
GL
GLM-4.5V
GLM · ggml-org
Params107B
Context64K
Q4_K_M63.6 GB
NE
Ea_Final_Nvidia_Nemotron_3_Super_120B_A12B_Bf16_030326_Vv0.1
Nemotron · ggml-org
Params121B
Context1024K
Smallest69.9 GB
LA
Laguna-S-2.1
Laguna · ggml-org
Params118B
Context1024K
Q4_K_M67.7 GB
GL
GLM-4.5-Air
GLM · ggml-org
Params107B
Context128K
Q4_K_M63.6 GB
GE
gemma-4-31B
Gemma · ggml-org
Params30.7B
Context256K
Smallest32.6 GB
QW
spec for testing
Qwen · ggml-org
Params1.92B
Context40K
Q4_K_M0.3 GB
QW
Qwen3.6 35B A3B
Qwen · ggml-org
Params447M
Context256K
Smallest37.8 GB
MI
Ministral 3 8B Reasoning 2512
Mistral · ggml-org
Params8.49B
Context256K
Smallest9.0 GB
QW
Qwen2.5 Coder 0.5B
Qwen · ggml-org
Params494M
Context32K
Smallest0.5 GB
DE
DeepSeek R1 Distill Qwen 1.5B
DeepSeek · ggml-org
Params1.78B
Context128K
Smallest1.1 GB
MI
Ministral 3 3B Reasoning 2512
Mistral · ggml-org
Params3.43B
Context256K
Smallest3.7 GB
LI
LightOnOCR 1B 1025
Lightonocr · ggml-org
Params752M
Context8K
Smallest0.8 GB
MI
Ministral 3 8B Instruct 2512
Mistral · ggml-org
Params8.49B
Context256K
Smallest9.0 GB
QW
Qwen3.5 0.8B Base
Qwen · ggml-org
Params773M
Context256K
Smallest0.6 GB
QW
Qwen2.5 Coder 14B Instruct
Qwen · ggml-org
Params14.8B
Context32K
Smallest15.7 GB
DO
Dots3 Note Prev
Dots · ggml-org
Params281B
Context512K
Q4_K_M169.9 GB
MI
Ministral 3 14B Reasoning 2512
Mistral · ggml-org
Params13.5B
Context256K
Smallest14.4 GB
QW
Qwen3 32B
Qwen · ggml-org
Params32.8B
Context40K
Q4_K_M19.8 GB
LF
LFM2 VL 450M
Lfm · ggml-org
Params354M
Context125K
Smallest0.4 GB
IN
InternVL2_5 4B
Internvl · ggml-org
Params3.4B
Context32K
Q4_K_M2.1 GB
QW
Qwen3-0.6B-Base
Qwen · ggml-org
Params596M
Context32K
Smallest0.6 GB
QW
Qwen3-8B-Base
Qwen · ggml-org
Params8.19B
Context32K
Smallest8.7 GB
MI
Ministral 3 14B Instruct 2512
Mistral · ggml-org
Params13.5B
Context256K
Smallest14.4 GB
QW
Qwen3.6 27B
Qwen · ggml-org
Params461M
Context256K
Smallest29.0 GB
QW
LoRA Qwen2.5 72B Instruct Abliterated
Qwen · ggml-org
Params433M
Context—
Smallest1.7 GB