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.

Most downloadedNewestLargestLongest contextSmallest
LL
Llama-3.1-8B
Llama · Mungert
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
MI
MiniCPM4-8B
MiniCPM · Mungert
Params8.19B
Context32K
Q4_K_M5.0 GB
GGUF
DE
DeepSeek-R1-Distill-Llama-8B
DeepSeek · Mungert
Params8.03B
Context128K
Q4_K_M5.1 GB
ReasoningTool use
QW
II-Search-4B
Qwen · Mungert
Params4.41B
Context96K
Q4_K_M3.0 GB
ReasoningTool use
AF
AFM-4.5B
Afm · Mungert
Params4.62B
Context64K
Q4_K_M3.0 GB
GGUF
TR
TriLM_1.1B_Unpacked
Trilm · Mungert
Params1.15B
Context2K
Q4_K_M0.7 GB
GGUF
LL
Llama-3.2-1B
Llama · Mungert
Params1.24B
Context128K
Q4_K_M0.8 GB
GGUF
QW
openhands-lm-7b-v0.1
Qwen · Mungert
Params7.62B
Context32K
Q4_K_M4.8 GB
CodingTool use
FU
functionary-v4r-small-preview
Functionary · Mungert
Params8.03B
Context128K
Q4_K_M5.1 GB
Tool use
TR
Trinity-Mini
Trinity · Mungert
Params26.1B
Context128K
Q4_K_M16.3 GB
ReasoningTool use
QW
instinct
Qwen · Mungert
Params7.62B
Context32K
Q4_K_M5.0 GB
CodingTool use
QW
Kevin-32B
Qwen · Mungert
Params32.8B
Context40K
Q4_K_M19.8 GB
ReasoningTool use
GR
granite-4.0-micro
Granite · Mungert
Params3.4B
Context128K
Q4_K_M2.1 GB
Tool use
GL
GLM 4.7
GLM · Mungert
Params360B
Context198K
Q4_K_M219.4 GB
GGUF
AB
Absolute_Zero_Reasoner-Coder-14b
Absolute · Mungert
Params14.8B
Context32K
Q4_K_M9.1 GB
Coding
AB
Absolute_Zero_Reasoner-Coder-7b
Absolute · Mungert
Params7.62B
Context32K
Q4_K_M4.8 GB
Coding
OU
OuteTTS-1.0-0.6B
Outetts · Mungert
Params602M
Context40K
Q4_K_M0.4 GB
GGUF
AB
Absolute_Zero_Reasoner-Coder-3b
Absolute · Mungert
Params3.09B
Context32K
Q4_K_M1.9 GB
Coding
FU
functionary-small-v3.1
Functionary · Mungert
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
MO
mOrpheus_3B-1Base_early_preview-v1-8600
Morpheus · Mungert
Params3.3B
Context128K
Q4_K_M2.1 GB
Tool use

Keep browsing