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.
IN
InternVL3-8B
Internvl · Mungert
Params7.61B
Context32K
Q4_K_M4.8 GB
QW
Nanonets-OCR-s
Qwen · Mungert
Params3.09B
Context125K
Q4_K_M1.9 GB
LL
Llama-3.1-Nemotron-Nano-8B-v1
Llama · Mungert
Params8.03B
Context128K
Q4_K_M5.1 GB
QW
Nemotron-Orchestrator-8B
Qwen · Mungert
Params8.19B
Context40K
Q4_K_M5.4 GB
GR
granite-20b-code-instruct-r1.1
Granite · Mungert
Params20.1B
Context8K
Q4_K_M12.6 GB
QE
QED-Nano
Qed · Mungert
Params4.02B
Context256K
Q4_K_M2.5 GB
GR
granite-3.0-2b-instruct
Granite · Mungert
Params2.63B
Context4K
Q4_K_M1.6 GB
TU
DR-Tulu-8B
Tulu · Mungert
Params8.19B
Context40K
Q4_K_M5.4 GB
QW
pokee_research_7b
Qwen · Mungert
Params7.6B
Context32K
Q4_K_M5.0 GB
QW
OCRFlux-3B
Qwen · Mungert
Params3.4B
Context125K
Q4_K_M2.2 GB
QW
VibeThinker-1.5B
Qwen · Mungert
Params1.78B
Context128K
Q4_K_M1.3 GB
QW
NextCoder-14B
Qwen · Mungert
Params14.8B
Context32K
Q4_K_M9.1 GB
AC
AceMath-1.5B-Instruct
Acemath · Mungert
Params1.78B
Context4K
Q4_K_M1.2 GB
GR
granite-20b-code-instruct-8k
Granite · Mungert
Params20.1B
Context8K
Q4_K_M12.6 GB
LL
Foundation-Sec-8B
Llama · Mungert
Params8.03B
Context128K
Q4_K_M5.1 GB
LL
Llama-3.1-70B-Instruct
Llama · Mungert
Params70.6B
Context128K
Q4_K_M42.8 GB
QW
nomic-embed-code
Qwen · Mungert
Params7.07B
Context32K
Q4_K_M4.3 GB
QW
Homunculus
Qwen · Mungert
Params12.5B
Context128K
Q4_K_M7.8 GB
GE
google_gemma-3-1b-it
Gemma · Mungert
Params1B
Context32K
Smallest0.7 GB
RW
rwkv7-2.9B-world
Rwkv · Mungert
Params2.95B
Context1024K
Q4_K_M1.9 GB
LL
Dolphin3.0-Llama3.2-3B
Llama · Mungert
Params3.21B
Context128K
Q4_K_M2.0 GB
QW
Qwen3-4B-Instruct-2507
Qwen · Mungert
Params4.02B
Context256K
Q4_K_M2.6 GB
TI
TildeOpen-30b
Tildeopen · Mungert
Params30.7B
Context64K
Q4_K_M19.0 GB
GR
granite-3.0-8b-instruct
Granite · Mungert
Params8.17B
Context4K
Q4_K_M4.9 GB
NA
Nanbeige4-3B-Thinking-2511
Nanbeige · Mungert
Params3.93B
Context64K
Q4_K_M2.7 GB
GR
granite-3.2-2b-instruct
Granite · Mungert
Params2.53B
Context128K
Q4_K_M1.5 GB
QW
Qwen3-30B-A3B-Instruct-2507
Qwen · Mungert
Params30.5B
Context256K
Q4_K_M19.0 GB
QW
Qwen3.5-0.8B
Qwen · Mungert
Params752M
Context256K
Q4_K_M0.5 GB
OR
Orchestrator-8B
Orchestrator · Mungert
Params8.2B
Context40K
Q4_K_M5.4 GB
QW
Skywork-SWE-32B
Qwen · Mungert
Params32.8B
Context32K
Q4_K_M19.8 GB