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
QW
NextCoder-7B
Qwen · Mungert
Params7.62B
Context32K
Q4_K_M4.8 GB
CodingTool use
GR
granite-3.3-8b-instruct
Granite · Mungert
Params8.17B
Context128K
Q4_K_M4.9 GB
ReasoningTool use
DE
Fathom-R1-14B
DeepSeek · Mungert
Params14.8B
Context128K
Q4_K_M9.1 GB
ReasoningTool use
QW
Qwen2.5-14B-Instruct
Qwen · Mungert
Params14.8B
Context32K
Q4_K_M9.0 GB
Tool use
QW
Qwen3.5-9B
Qwen · Mungert
Params8.95B
Context256K
Q4_K_M6.0 GB
ReasoningTool useVision
DE
DeepSeek-R1-Distill-Qwen-32B
DeepSeek · Mungert
Params32.8B
Context128K
Q4_K_M20.1 GB
ReasoningTool use
QW
MiroThinker-1.7-mini
Qwen · Mungert
Params30.5B
Context256K
Q4_K_M18.9 GB
ReasoningTool use
OR
orpheus-finetuned-3b
Orpheus · Mungert
Params3.78B
Context128K
Q4_K_M2.5 GB
GGUF
PH
phi 4
Phi · Mungert
Params14.7B
Context16K
Q4_K_M9.1 GB
Coding
DE
DeepCoder-1.5B-Preview
DeepSeek · Mungert
Params1.78B
Context128K
Q4_K_M1.2 GB
CodingReasoningTool use
MI
Harbinger-24B
Mistral · Mungert
Params23.6B
Context128K
Q4_K_M14.3 GB
Roleplay
MI
MiMo-Embodied-7B
Mimo · Mungert
Params7.62B
Context125K
Q4_K_M5.1 GB
Tool use
LF
LFM2-2.6B-Exp
Lfm · Mungert
Params2.7B
Context125K
Q4_K_M1.7 GB
Tool use
MI
Ministral-3-14B-Reasoning-2512
Mistral · Mungert
Params13.5B
Context256K
Q4_K_M8.7 GB
ReasoningTool use
QW
OpenCodeReasoning-Nemotron-32B-IOI
Qwen · Mungert
Params32.8B
Context32K
Q4_K_M19.8 GB
CodingReasoningTool use
DE
DeepSeek-R1-Distill-Qwen-1.5B
DeepSeek · Mungert
Params1.78B
Context128K
Q4_K_M1.2 GB
ReasoningTool use
LF
LFM2-2.6B
Lfm · Mungert
Params2.57B
Context125K
Q4_K_M1.6 GB
Tool use
QW
Qwen3 Embedding 8B Bf16
Qwen · Mungert
Params7.57B
Context40K
Q4_K_M4.6 GB
EmbeddingTool use
QW
WEBGEN-4B-Preview
Qwen · Mungert
Params4.02B
Context256K
Q4_K_M2.6 GB
ReasoningTool use
MI
Magistral-Small-2506-abliterated
Mistral · Mungert
Params23.6B
Context40K
Q4_K_M14.3 GB
Reasoning
SM
SmolVLM-256M-Instruct
SmolLM · Mungert
Params163M
Context8K
Q4_K_M0.1 GB
Vision
QW
MiroThinker-v1.0-30B
Qwen · Mungert
Params30.5B
Context256K
Q4_K_M19.0 GB
ReasoningTool use
QW
Qwen3-30B-A6B-16-Extreme
Qwen · Mungert
Params30.5B
Context40K
Q4_K_M18.9 GB
ReasoningTool use
LL
Llama-xLAM-2-8b-fc-r
Llama · Mungert
Params8.03B
Context128K
Q4_K_M5.0 GB
Tool use
QW
Qwen3 Embedding 4B Bf16
Qwen · Mungert
Params4.02B
Context40K
Q4_K_M2.5 GB
EmbeddingTool use
QW
Qwen3-VL-2B-Instruct
Qwen · Mungert
Params1.72B
Context256K
Q4_K_M1.2 GB
Tool useVision
GL
GLM-4.6V-Flash
GLM · Mungert
Params9.4B
Context128K
Q4_K_M6.6 GB
ReasoningTool useVision
GL
AutoGLM-Phone-9B
GLM · Mungert
Params9.4B
Context64K
Q4_K_M6.6 GB
Vision
LL
Llama-3.3-70B-Instruct
Llama · Mungert
Params70.6B
Context128K
Q4_K_M42.8 GB
Tool use
MI
MiraTTS
Miratts · Mungert
Params507M
Context32K
Q4_K_M0.4 GB
Tool use

Keep browsing