GGUF models by mmnga-o
38 GGUF models quantized by mmnga-o on Hugging Face. Sizes run from 24M to 1420B parameters. The longest trained context is 1024K tokens.
GP
GPT OSS Swallow 20B SFT v0.1
gpt-oss · mmnga-o
Params20.9B
Context128K
Q4_K_M15.8 GB
KA
Karakuri Vl 2 8b Thinking 2603
Karakuri · mmnga-o
Params8.19B
Context256K
Q4_K_M5.0 GB
DE
DeepSeek V4 Flash 0731 REAP W
DeepSeek · mmnga-o
Params155B
Context1024K
Smallest55.0 GB
CA
CAT Translate 3.3b Beta
Cat · mmnga-o
Params3.36B
Context8K
Q4_K_M2.1 GB
KI
Kimi-K3
Kimi · mmnga-o
Params1420B
Context1024K
Smallest326.9 GB
WA
wavlm base plus
Wavlm · mmnga-o
Params24M
Context—
Smallest0.1 GB
QW
Qwen3.8 REAP30 Width50 UD
Qwen · mmnga-o
Params878B
Context256K
Smallest159.0 GB
GP
Gpt Oss 20b Ja Fin Thinking
gpt-oss · mmnga-o
Params20.9B
Context128K
Smallest12.1 GB