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.

Most downloadedNewestLargestLongest contextSmallest
LL
Llama 3.1 Nemotron 70B Instruct HF
Llama · mmnga
Params70.6B
Context128K
Q4_K_M42.5 GB
Tool use
AY
aya-23-8B
Aya · mmnga
Params8.03B
Context8K
Q4_K_M5.1 GB
GGUF
PH
Phi 4 Open R1 Distill EZOv1
Phi · mmnga
Params14.7B
Context16K
Q4_K_M9.1 GB
Reasoning
CO
codegemma-7b-it
Codegemma · mmnga
Params8.54B
Context8K
Q4_K_M5.3 GB
GGUF
WA
watashiha-gpt-6b
Watashiha · mmnga
Params6.01B
Context2K
Q4_K_M3.9 GB
GGUF
LL
llm jp 3.1 8x13b instruct4
Llm · mmnga
Params73.2B
Context4K
Q4_K_M45.4 GB
GGUF
KA
ao-karasu-72B
Karasu · mmnga
Params72.3B
Context32K
Q4_K_M44.1 GB
GGUF
JA
japanese-gpt-neox-3.6b
Japanese · mmnga
Params3.61B
Context2K
Smallest2.1 GB
GGUF
LL
llm-jp-13b-instruct-full-dolly-ichikara_004_001_single-oasst-oasst2-v2.0
Llm · mmnga
Params13.7B
Context4K
Q4_K_M8.3 GB
GGUF
DE
DeepSeek V3 Slice Jp64
DeepSeek · mmnga
Params181B
Context160K
Q4_K_M108.6 GB
Tool use
JA
japanese stablelm instruct gamma 7b
Japanese · mmnga
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
DE
Phi 4 Deepseek R1K RL EZO
DeepSeek · mmnga
Params14.7B
Context16K
Q4_K_M9.1 GB
GGUF
BI
bilingual-gpt-neox-4b-instruction-ppo
Bilingual · mmnga
Params3.8B
Context2K
Smallest2.2 GB
GGUF
LL
ELYZA japanese Llama 2 13b fast
Llama · mmnga
Params13.1B
Context4K
Q4_K_M8.0 GB
GGUF
SK
Sky T1 32B Preview
Sky · mmnga
Params32.8B
Context32K
Q4_K_M19.9 GB
Tool use
MI
Mistral Nemo Instruct 2407
Mistral · mmnga
Params12.2B
Context1000K
Smallest3.0 GB
GGUF
DE
Deepseek R1 Distill Qwen2.5 Bakeneko 32b
DeepSeek · mmnga
Params32.8B
Context128K
Q4_K_M19.9 GB
ReasoningTool use
SU
Superswallow 13b v0.1
Superswallow · mmnga
Params13.1B
Context4K
Q4_K_M7.9 GB
GGUF
GE
EZO-Common-9B-gemma-2-it
Gemma · mmnga
Params9.24B
Context8K
Q4_K_M5.8 GB
GGUF
KA
Karakuri Lm 32b Thinking 2501 Exp
Karakuri · mmnga
Params32.8B
Context32K
Q4_K_M19.9 GB
ReasoningTool use
MI
aixsatoshi Swallow MX 8x7b NVE chatvector Mixtral instruct v2
Mistral · mmnga
Params46.7B
Context32K
Q4_K_M28.4 GB
GGUF
MA
matsuolab weblab 10b
Matsuolab · mmnga
Params10.7B
Context—
Smallest6.0 GB
GGUF
BI
bilingual-gpt-neox-4b
Bilingual · mmnga
Params3.8B
Context2K
Smallest2.2 GB
GGUF
WA
WabiSabi V1
Wabisabi · mmnga
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
GE
gemma-1.1-7b-it
Gemma · mmnga
Params8.54B
Context8K
Q4_K_M5.3 GB
GGUF
NA
napopoa32 swallow hermes st v1
Napopoa · mmnga
Params7.33B
Context4K
Q4_K_M4.4 GB
Tool use
TO
tokyotech llm Swallow MS 7b v0.1
Tokyotech · mmnga
Params7.33B
Context4K
Q4_K_M4.4 GB
GGUF
AI
aixsatoshi Honyaku 7b v2
Aixsatoshi · mmnga
Params7.33B
Context4K
Q4_K_M4.4 GB
GGUF
LL
llm-jp-13b-instruct-dolly-en-ja-oasst-v1.1
Llm · mmnga
Params13.1B
Context2K
Q4_K_M8.4 GB
GGUF
KA
karakuri lm 70b chat v0.1
Karakuri · mmnga
Params69.2B
Context4K
Q4_K_M41.6 GB
GGUF

Keep browsing