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.
GE
Gemma 3 1b It
Gemma · AmpereComputing
Params1B
Context32K
Smallest1.0 GB
DE
DeepSeek R1 Distill Qwen 7B
DeepSeek · AmpereComputing
Params7.62B
Context128K
Smallest7.7 GB
QW
Qwen3 4B
Qwen · AmpereComputing
Params4.02B
Context40K
Smallest4.1 GB
QW
qwen 3 a3b 30b instruct
Qwen · AmpereComputing
Params30.5B
Context256K
Smallest31.0 GB
DE
Deepseek-V3.1
DeepSeek · AmpereComputing
Params671B
Context160K
Smallest676.6 GB
LL
Llama 3.1 8B Instruct
Llama · AmpereComputing
Params8.03B
Context128K
Smallest8.1 GB
QW
Qwen2.5 3B Instruct
Qwen · AmpereComputing
Params3.09B
Context32K
Smallest3.1 GB
QW
qwen 3 coder a3b 30b instruct
Qwen · AmpereComputing
Params30.5B
Context256K
Smallest31.0 GB
GR
Granite 4.0 H Small
Granite · AmpereComputing
Params32.2B
Context1024K
Smallest32.7 GB
QW
qwen 3 4b 2507 instruct
Qwen · AmpereComputing
Params4.02B
Context256K
Smallest4.1 GB
GR
granite-8b-code-instruct-128k
Granite · AmpereComputing
Params8.05B
Context125K
Smallest8.1 GB
QW
Qwen3 8B
Qwen · AmpereComputing
Params8.19B
Context40K
Smallest8.3 GB
QW
Qwen3 1.7B
Qwen · AmpereComputing
Params2.03B
Context40K
Smallest2.1 GB
DE
DeepSeek R1 Distill Llama 70B
DeepSeek · AmpereComputing
Params70.6B
Context128K
Smallest71.1 GB
QW
Qwen2.5 0.5B Instruct
Qwen · AmpereComputing
Params494M
Context32K
Smallest0.5 GB
RA
RakutenAI 7B Chat
Rakutenai · AmpereComputing
Params7.37B
Context32K
Smallest7.4 GB
MI
mistral small 3.2 2506 24b instruct
Mistral · AmpereComputing
Params23.6B
Context128K
Smallest23.8 GB
GR
Granite 4.0 Tiny Preview
Granite · AmpereComputing
Params6.67B
Context1024K
Smallest6.7 GB
QW
Qwen2.5 7B Instruct
Qwen · AmpereComputing
Params7.62B
Context32K
Smallest7.7 GB
QW
Qwen2.5 32B Instruct
Qwen · AmpereComputing
Params32.8B
Context32K
Smallest33.0 GB
QW
qwen 3 4b 2507 thinking
Qwen · AmpereComputing
Params4.02B
Context256K
Smallest4.1 GB
QW
qwen 3 a3b 30b thinking
Qwen · AmpereComputing
Params30.5B
Context256K
Smallest31.0 GB
DE
DeepSeek V3 0324 BF16
DeepSeek · AmpereComputing
Params671B
Context160K
Smallest676.6 GB
BI
bielik v3.0 4.5b instruct
Bielik · AmpereComputing
Params4.76B
Context32K
Smallest4.8 GB
QW
Qwen3 0.6B
Qwen · AmpereComputing
Params752M
Context40K
Smallest0.8 GB
DE
DeepSeek R1 0528 Qwen3 8B
DeepSeek · AmpereComputing
Params8.19B
Context128K
Smallest8.3 GB
DE
DeepSeek R1 Distill Llama 8B
DeepSeek · AmpereComputing
Params8.03B
Context128K
Smallest8.1 GB
DE
DeepSeek R1 Distill Qwen 32B
DeepSeek · AmpereComputing
Params32.8B
Context128K
Smallest33.0 GB
DE
DeepSeek R1 Distill Qwen 1.5B
DeepSeek · AmpereComputing
Params1.78B
Context128K
Smallest1.8 GB
GR
Granite 3.3 2b Instruct
Granite · AmpereComputing
Params2.53B
Context128K
Smallest2.6 GB