GGUF models by mmnga
261 GGUF models quantized by mmnga on Hugging Face. Sizes run from 268M to 671B parameters. The longest trained context is 10240K tokens.
LL
Llama 3.1 Swallow 70B Instruct v0.1
Llama · mmnga
Params70.6B
Context8K
Q4_K_M42.5 GB
HA
HachiML youri 2x7b v0.2
Hachiml · mmnga
Params11.1B
Context4K
Q4_K_M6.7 GB
CY
cyberagent calm2 7b chat dpo experimental
Cyberagent · mmnga
Params7.01B
Context32K
Q4_K_M4.3 GB
LL
Llama 3.1 Swallow 70B Instruct v0.3
Llama · mmnga
Params70.6B
Context128K
Q4_K_M42.5 GB
RA
RakutenAI 7B chat
Rakutenai · mmnga
Params7.37B
Context32K
Q4_K_M4.5 GB
QW
Qwen3 EZO 8B Beta
Qwen · mmnga
Params8.19B
Context40K
Q4_K_M5.0 GB
LL
Gemma 2 Llama Swallow 9b It v0.1
Llama · mmnga
Params9.24B
Context8K
Q4_K_M5.8 GB
DE
RoguePlanet DeepSeek R1 Qwen 32B
DeepSeek · mmnga
Params32.8B
Context128K
Q4_K_M19.9 GB
DE
DeepSeek R1 Distill Qwen 14B
DeepSeek · mmnga
Params14.8B
Context128K
Q4_K_M9.0 GB
SH
shisa 7b v1
Shisa · mmnga
Params7.96B
Context32K
Q4_K_M4.9 GB
CA
calm2-7b
Calm · mmnga
Params7.01B
Context4K
Q4_K_M4.3 GB
QW
Preferred MedLLM Qwen 72B
Qwen · mmnga
Params72.7B
Context128K
Q4_K_M47.4 GB
GE
Gemma 3n E4B It
Gemma · mmnga
Params6.87B
Context32K
Q4_K_M4.2 GB
LL
Gemma 2 Llama Swallow 2b It v0.1
Llama · mmnga
Params2.61B
Context8K
Q4_K_M1.7 GB
LL
Llm Jp 3 8x13b Instruct3
Llm · mmnga
Params73.2B
Context4K
Q4_K_M45.4 GB
AY
aya-23-35B
Aya · mmnga
Params35B
Context8K
Q4_K_M21.5 GB
QW
Qwen2.5 Bakeneko 32b Instruct v2
Qwen · mmnga
Params32.8B
Context32K
Q4_K_M19.9 GB
QW
Qwq Bakeneko 32b
Qwen · mmnga
Params32.8B
Context128K
Q4_K_M19.9 GB
DA
datagemma rag 27b it
Datagemma · mmnga
Params27.2B
Context8K
Q4_K_M16.6 GB
LL
Reflection Llama 3.1 70B
Llama · mmnga
Params70.6B
Context8K
Q4_K_M42.5 GB
QW
ELYZA Shortcut 1.0 Qwen 32B
Qwen · mmnga
Params32.8B
Context32K
Q4_K_M19.9 GB
DE
DeepSeek R1 Distill Qwen 1.5B
DeepSeek · mmnga
Params1.78B
Context128K
Q4_K_M1.1 GB
QW
Qwen2.5 Bakeneko 32b
Qwen · mmnga
Params32.8B
Context128K
Q4_K_M19.9 GB
DE
DeepSeek R1 Distill Qwen 7B
DeepSeek · mmnga
Params7.62B
Context128K
Q4_K_M4.7 GB
AI
aixsatoshi calm2 7b chat 7b moe
Aixsatoshi · mmnga
Params11.3B
Context32K
Q4_K_M6.9 GB
QW
Cogito v1 Preview Qwen 14B
Qwen · mmnga
Params14.8B
Context128K
Q4_K_M9.0 GB
JA
japanese-gpt-neox-3.6b-instruction-ppo
Japanese · mmnga
Params3.61B
Context2K
Smallest2.1 GB
GE
gemma-7b-it
Gemma · mmnga
Params8.54B
Context8K
Q4_K_M5.1 GB
ER
ERNIE 4.5 21B A3B Thinking
Ernie · mmnga
Params21.8B
Context128K
Q4_K_M13.2 GB
QW
QwQ 32B
Qwen · mmnga
Params32.8B
Context128K
Q4_K_M19.9 GB