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-3.2-3B-Instruct
Llama · Mungert
Params3.21B
Context128K
Q4_K_M2.0 GB
Tool use
GR
granite-3b-code-base-2k
Granite · Mungert
Params3.48B
Context2K
Q4_K_M2.1 GB
Coding
PL
PLM-1.8B-Instruct
Plm · Mungert
Params1.83B
Context4K
Q4_K_M1.2 GB
GGUF
LI
Lingshu-32B
Lingshu · Mungert
Params32.8B
Context125K
Q4_K_M19.8 GB
ReasoningVision
GR
granite-20b-functioncalling
Granite · Mungert
Params20.1B
Context8K
Q4_K_M12.6 GB
GGUF
ME
MedScholar-1.5B
Medscholar · Mungert
Params1.54B
Context32K
Q4_K_M1.0 GB
GGUF
QW
OpenReasoning-Nemotron-1.5B
Qwen · Mungert
Params1.54B
Context128K
Q4_K_M1.0 GB
CodingReasoning
GR
granite-guardian-3.1-2b
Granite · Mungert
Params2.53B
Context128K
Q4_K_M1.5 GB
Tool use
QW
typhoon-ocr-7b
Qwen · Mungert
Params7.62B
Context125K
Q4_K_M4.8 GB
Vision
AL
all-MiniLM-L6-v2
All · Mungert
Params23M
Context512
Q4_K_M0.0 GB
CodingEmbedding
LL
Llama-3.2-3B-F1-Reasoning-Instruct
Llama · Mungert
Params3.61B
Context128K
Q4_K_M2.3 GB
ReasoningTool use
GR
granite-3.1-8b-instruct
Granite · Mungert
Params8.17B
Context128K
Q4_K_M4.9 GB
Tool use
ME
MetaStone-L1-7B
Metastone · Mungert
Params7.62B
Context128K
Q4_K_M4.7 GB
ReasoningTool use
LF
LFM2.5-1.2B-Thinking
Lfm · Mungert
Params1.17B
Context125K
Q4_K_M0.7 GB
ReasoningTool use
QW
Nanonets-OCR2-1.5B-exp
Qwen · Mungert
Params982M
Context32K
Q4_K_M0.7 GB
Vision
GE
sarvam-translate
Gemma · Mungert
Params3.88B
Context128K
Q4_K_M2.5 GB
GGUF
QW
Arch-Agent-32B
Qwen · Mungert
Params32.8B
Context32K
Q4_K_M19.8 GB
Coding
GE
Gemma-3-Gaia-PT-BR-4b-it
Gemma · Mungert
Params3.88B
Context128K
Q4_K_M2.5 GB
GGUF
LL
DeepHermes-3-Llama-3-8B-Preview
Llama · Mungert
Params8.03B
Context128K
Q4_K_M5.1 GB
ReasoningRoleplayTool use
GR
granite-guardian-3.2-5b
Granite · Mungert
Params5.78B
Context128K
Q4_K_M3.5 GB
Tool use
GR
granite-3.0-1b-a400m-base
Granite · Mungert
Params1.38B
Context4K
Smallest0.6 GB
GGUF
NE
Nemotron-4-Mini-Hindi-4B-Base
Nemotron · Mungert
Params4.19B
Context4K
Q4_K_M2.9 GB
Tool use
GR
granite-3.1-1b-a400m-instruct
Granite · Mungert
Params1.33B
Context128K
Smallest0.5 GB
Tool use
GR
granite-4.0-350m
Granite · Mungert
Params352M
Context32K
Q4_K_M0.3 GB
Tool use
LL
Meta-Llama-3-8B
Llama · Mungert
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
QW
UIGEN-T2-7B
Qwen · Mungert
Params7.62B
Context32K
Q4_K_M4.8 GB
CodingTool use
MI
Wayfarer-2-12B
Mistral · Mungert
Params12.2B
Context128K
Q4_K_M7.9 GB
Roleplay
MA
MAI-UI-8B
Mai · Mungert
Params8.19B
Context256K
Q4_K_M5.4 GB
Tool use
QW
LiveCC-7B-Instruct
Qwen · Mungert
Params7.62B
Context32K
Q4_K_M4.8 GB
Vision
QW
OpenCodeReasoning-Nemotron-7B
Qwen · Mungert
Params7.62B
Context32K
Q4_K_M4.8 GB
CodingReasoningTool use

Keep browsing