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
TA
UI-TARS-1.5-7B
Tars · Mungert
Params7.6B
Context125K
Q4_K_M4.8 GB
Vision
QW
Qwen2.5-VL-3B-Instruct
Qwen · Mungert
Params3.1B
Context125K
Q4_K_M1.9 GB
Vision
HU
Hunyuan-MT-7B
Hunyuan · Mungert
Params7.5B
Context256K
Q4_K_M4.7 GB
GGUF
QW
Qwen2.5-14B-Instruct-1M
Qwen · Mungert
Params14.8B
Context986K
Q4_K_M9.2 GB
GGUF
QW
Qwen2.5-7B-Instruct-1M
Qwen · Mungert
Params7.6B
Context986K
Q4_K_M4.8 GB
GGUF
QW
GELab-Zero-4B-preview
Qwen · Mungert
Params4B
Context256K
Q4_K_M2.6 GB
Vision
QW
Qwen2.5-VL-7B-Instruct
Qwen · Mungert
Params7.6B
Context125K
Q4_K_M4.8 GB
Vision
QW
Qwen3-Coder-Next
Qwen · Mungert
Params79.7B
Context256K
Q4_K_M49.2 GB
CodingTool use
OR
Ornith-1.5-9B
Ornith · Mungert
Params9.2B
Context256K
Q4_K_M6.1 GB
GGUF
PA
PaddleOCR-VL-1.6
Paddleocr · Mungert
Params467M
Context128K
Q4_K_M0.4 GB
Vision
QW
Qwen3-4B-abliterated
Qwen · Mungert
Params4B
Context40K
Q4_K_M2.5 GB
GGUF
PH
phi-4-mini-instruct
Phi · Mungert
Params3.84B
Context128K
Q4_K_M2.5 GB
CodingReasoning
QW
MiroThinker-v1.5-30B
Qwen · Mungert
Params30.5B
Context256K
Q4_K_M18.9 GB
Reasoning
MI
Ministral-3-3B-Reasoning-2512
Mistral · Mungert
Params3.43B
Context256K
Q4_K_M2.2 GB
Reasoning
QW
Jan-v2-VL-high
Qwen · Mungert
Params8.2B
Context256K
Q4_K_M5.4 GB
ReasoningVision
MI
Ministral-3-8B-Reasoning-2512
Mistral · Mungert
Params8.5B
Context256K
Q4_K_M5.5 GB
Reasoning
OL
Olmo-3-1025-7B
OLMo · Mungert
Params7.3B
Context64K
Q4_K_M4.7 GB
GGUF
GL
GLM-ASR-Nano-2512
GLM · Mungert
Params1.59B
Context8K
Q4_K_M1.1 GB
GGUF
QW
DMind-3-mini
Qwen · Mungert
Params4B
Context256K
Q4_K_M2.5 GB
Reasoning
QW
Strand-Rust-Coder-14B-v1
Qwen · Mungert
Params14.8B
Context32K
Q4_K_M9.3 GB
Coding
QW
Fathom-Search-4B
Qwen · Mungert
Params4B
Context40K
Q4_K_M2.6 GB
GGUF
QW
Qwen2.5-3B-Instruct
Qwen · Mungert
Params3.1B
Context32K
Q4_K_M1.9 GB
GGUF
MI
MiniCPM5-2B
MiniCPM · Mungert
Params2.52B
Context128K
Q4_K_M1.7 GB
CodingTool use
QW
Qwen3-8B-abliterated
Qwen · Mungert
Params8.2B
Context40K
Q4_K_M5.2 GB
GGUF
GP
DMind-3
gpt-oss · Mungert
Params20.9B
Context128K
Q4_K_M16.0 GB
GGUF
MI
Dolphin-Mistral-24B-Venice-Edition
Mistral · Mungert
Params23.6B
Context32K
Q4_K_M14.5 GB
GGUF
GR
granite-4.0-micro-base
Granite · Mungert
Params3.4B
Context128K
Q4_K_M2.1 GB
GGUF
GE
gemma-4-12B-it
Gemma · Mungert
Params11.9B
Context256K
Q4_K_M7.7 GB
GGUF
LL
Llama-3.3-8B-Instruct
Llama · Mungert
Params8B
Context8K
Q4_K_M5.3 GB
GGUF
QW
Qwen3.5-35B-A3B
Qwen · Mungert
Params34.7B
Context256K
Q4_K_M21.6 GB
Vision

About Mungert on Hugging Face

Mungert has published 440 GGUF models that ggufmodels.com tracks, across families such as Qwen, Granite and Llama. The most downloaded are UI-TARS-1.5-7B, Qwen2.5-VL-3B-Instruct and Hunyuan-MT-7B.

The quants Mungert publishes most often are BF16 (437), F16 (436), Q4_1 (435) and Q4_0 (435). Their Q4_K_M files range from 0.0 to 219.4 GB. Parameter counts run from 23M to 360B, and the longest trained context window is 4192K tokens.

Frequently asked questions

What GGUF models has Mungert published?

440 models are listed here, mainly from the Qwen, Granite and Llama families. The most downloaded is UI-TARS-1.5-7B.

Which quants does Mungert publish?

The most common are BF16 (437 models), F16 (436 models), Q4_1 (435 models) and Q4_0 (435 models).

Keep browsing