GGUF models by AmpereComputing

68 GGUF models quantized by AmpereComputing on Hugging Face. Sizes run from 494M to 671B parameters. The longest trained context is 10240K tokens.

Most downloadedNewestLargestLongest contextSmallest
QW
QwQ 32B
Qwen · AmpereComputing
Params32.8B
Context40K
Smallest33.0 GB
ReasoningTool use
QW
Qwen3 14B
Qwen · AmpereComputing
Params14.8B
Context40K
Smallest14.9 GB
ReasoningTool use
RA
RakutenAI 7B Instruct
Rakutenai · AmpereComputing
Params7.37B
Context32K
Smallest7.4 GB
GGUF
MI
mistral nemo 2407 instruct
Mistral · AmpereComputing
Params12.2B
Context128K
Smallest12.4 GB
Tool use
GR
Granite 3.3 8b Instruct
Granite · AmpereComputing
Params8.17B
Context128K
Smallest8.2 GB
ReasoningTool use
PH
Phi 4 Mini Instruct
Phi · AmpereComputing
Params3.84B
Context128K
Smallest3.9 GB
Tool use
RA
RakutenAI 7B
Rakutenai · AmpereComputing
Params7.37B
Context32K
Smallest7.4 GB
GGUF
LL
Llama-3.3-70B-Instruct
Llama · AmpereComputing
Params70.6B
Context128K
Smallest71.1 GB
Tool use

Keep browsing