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.
DE
QwenLong-L1-32B
DeepSeek · Mungert
Params32.8B
Context128K
Q4_K_M19.8 GB
GR
granite-3b-code-instruct-128k
Granite · Mungert
Params3.48B
Context125K
Q4_K_M2.1 GB
FI
Fin R1
Fin · Mungert
Params7.62B
Context32K
Q4_K_M4.7 GB
XL
xLAM-2-3b-fc-r
Xlam · Mungert
Params3.09B
Context32K
Q4_K_M1.9 GB
SM
SmolVLM-Instruct
SmolLM · Mungert
Params1.81B
Context16K
Q4_K_M1.1 GB
OR
orpheus-3b-0.1-ft
Orpheus · Mungert
Params3.78B
Context128K
Q4_K_M2.5 GB
QW
Qwen3-30B-A3B
Qwen · Mungert
Params30.5B
Context40K
Q4_K_M19.0 GB
GR
granite-7b-instruct
Granite · Mungert
Params6.74B
Context4K
Q4_K_M4.1 GB
RW
rwkv7-1.5B-world
Rwkv · Mungert
Params1.53B
Context1024K
Q4_K_M1.0 GB
LL
Llama-3.1-Minitron-4B-Width-Base
Llama · Mungert
Params4.51B
Context128K
Q4_K_M2.9 GB
GE
gemma-3n-E4B-it
Gemma · Mungert
Params6.87B
Context32K
Q4_K_M4.8 GB
GR
granite-3.1-8b-base
Granite · Mungert
Params8.17B
Context128K
Q4_K_M4.9 GB
GE
medgemma-27b-text-it
Gemma · Mungert
Params27B
Context128K
Q4_K_M16.3 GB
QW
OlympicCoder-32B
Qwen · Mungert
Params32.8B
Context32K
Q4_K_M20.1 GB
SM
SmallThinker-21BA3B-Instruct
Smallthinker · Mungert
Params21.5B
Context16K
Q4_K_M13.6 GB
GR
granite-8b-code-instruct-128k
Granite · Mungert
Params8.05B
Context125K
Q4_K_M4.8 GB
SM
SmolVLM-500M-Instruct
SmolLM · Mungert
Params409M
Context8K
Q4_K_M0.3 GB
QW
Qwen3-14B
Qwen · Mungert
Params14.8B
Context40K
Q4_K_M9.2 GB
LL
Meta-Llama-3-8B-Instruct
Llama · Mungert
Params8.03B
Context8K
Q4_K_M5.0 GB
ME
medgemma-4b-it
Medgemma · Mungert
Params3.88B
Context128K
Q4_K_M2.5 GB
KA
KAT Dev 72B Exp
Kat · Mungert
Params72.7B
Context128K
Smallest0.0 GB
DE
FairyR1-32B
DeepSeek · Mungert
Params32.8B
Context128K
Q4_K_M19.8 GB
FU
functiongemma-270m-it
Functiongemma · Mungert
Params268M
Context32K
Q4_K_M0.3 GB
LL
Llama-3.2-1B-Instruct
Llama · Mungert
Params1.24B
Context128K
Q4_K_M0.8 GB
GE
google_gemma-3-12b-it
Gemma · Mungert
Params11.8B
Context128K
Q4_K_M7.3 GB
QW
Qwen3 Coder 30B A3B Instruct
Qwen · Mungert
Params30.5B
Context256K
Smallest0.1 GB
MI
Magistral Small 2506
Mistral · Mungert
Params23.6B
Context32K
Q4_K_M14.3 GB
GL
GLM-Z1-9B-0414
GLM · Mungert
Params9.4B
Context32K
Q4_K_M6.3 GB
SM
SmolDocling-256M-preview
Smolvlm · Mungert
Params163M
Context8K
Q4_K_M0.1 GB
QW
OpenMath-Nemotron-7B
Qwen · Mungert
Params7.62B
Context128K
Q4_K_M4.8 GB