GGUF models by Mungert
440 GGUF models quantized by Mungert on Hugging Face. Sizes run from 23M to 360B parameters. The longest trained context is 4192K tokens.
QW
LongWriter-Zero-32B
Qwen · Mungert
Params32.8B
Context32K
Q4_K_M19.8 GB
GR
granite-20b-code-base-r1.1
Granite · Mungert
Params20.1B
Context8K
Q4_K_M12.6 GB
DE
Polaris-7B-Preview
DeepSeek · Mungert
Params7.62B
Context128K
Q4_K_M4.8 GB
LL
Llama-Guard-3-8B
Llama · Mungert
Params8.03B
Context128K
Q4_K_M4.9 GB
GR
granite-3.0-3b-a800m-base
Granite · Mungert
Params3.37B
Context4K
Smallest1.2 GB
GR
granite-3.1-3b-a800m-base
Granite · Mungert
Params3.3B
Context128K
Smallest1.2 GB
LL
Llama-3.1-Nemotron-Nano-4B-v1.1
Llama · Mungert
Params4.51B
Context128K
Q4_K_M2.9 GB
GE
gemma 3 270m it
Gemma · Mungert
Params268M
Context32K
Smallest0.0 GB
MI
Mistral-NeMo-Minitron-8B-Instruct
Mistral · Mungert
Params8.41B
Context8K
Q4_K_M5.2 GB
GR
granite-4.0-h-1b
Granite · Mungert
Params1.46B
Context1024K
Q4_K_M0.9 GB
AC
AceInstruct-1.5B
Aceinstruct · Mungert
Params1.78B
Context128K
Q4_K_M1.2 GB
QW
UIGEN-X-4B-0729
Qwen · Mungert
Params4.41B
Context40K
Q4_K_M2.8 GB
LL
Llama-3.1-Nemotron-8B-UltraLong-4M-Instruct
Llama · Mungert
Params8.04B
Context4192K
Q4_K_M5.1 GB
LL
cogito-v1-preview-llama-8B
Llama · Mungert
Params8.03B
Context128K
Q4_K_M5.1 GB
LL
Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct
Llama · Mungert
Params8.04B
Context1048K
Q4_K_M5.1 GB
MI
MiniCPM4-0.5B
MiniCPM · Mungert
Params434M
Context32K
Q4_K_M0.3 GB
LL
Llama-3.1-Nemotron-8B-UltraLong-2M-Instruct
Llama · Mungert
Params8.04B
Context2096K
Q4_K_M5.1 GB
QW
OpenReasoning-Nemotron-7B
Qwen · Mungert
Params7.62B
Context128K
Q4_K_M4.8 GB
MI
sarvam-m
Mistral · Mungert
Params23.6B
Context32K
Q4_K_M14.3 GB
MI
Mistral-Crab-DPO
Mistral · Mungert
Params7.25B
Context32K
Q4_K_M4.4 GB
LL
watt-tool-8B
Llama · Mungert
Params8.03B
Context128K
Q4_K_M5.1 GB
DI
DiffuCoder-7B-Instruct
Diffucoder · Mungert
Params7.62B
Context128K
Q4_K_M4.8 GB
TR
trlm-135m
Trlm · Mungert
Params135M
Context8K
Q4_K_M0.1 GB
QW
OpenMath-Nemotron-1.5B
Qwen · Mungert
Params1.54B
Context128K
Q4_K_M1.0 GB
HU
Hunyuan-MT-Chimera-7B
Hunyuan · Mungert
Params7.5B
Context256K
Q4_K_M4.7 GB
QW
Qwen3-4B-Thinking-2507
Qwen · Mungert
Params4.02B
Context256K
Q4_K_M2.6 GB
RO
RoboBrain2.0-7B
Robobrain · Mungert
Params7.62B
Context125K
Q4_K_M4.8 GB
QW
Qwen3.6-27B
Qwen · Mungert
Params27.3B
Context256K
Q4_K_M18.1 GB
QW
OpenCodeReasoning-Nemotron-32B
Qwen · Mungert
Params32.8B
Context32K
Q4_K_M19.8 GB
QW
limbic tool use 0.5B 32K
Qwen · Mungert
Params494M
Context32K
Smallest0.0 GB