Hugging Face's logo
AmpereComputing 's Collections
AFM 4.5B
Bielik v3.0
DeepSeek R1
DeepSeek V3
DeepSeek V3.1
ERNIE 4.5
Gemma 3
GLM 4.5
GPT-OSS
Granite 3.3
Granite 4.0
Llama 3.1
Llama 3.2
Llama 3.3
Llama 4
Mistral
Phi 4
RakutenAI 7B
Qwen 2.5
Qwen 3
QwQ

Granite 4.0

Ampere's quantization formats (Q4_K_4 / Q8R16) require Ampere optimized llama.cpp available here: https://hub.docker.com/r/amperecomputingai/llama.cpp

Upvote
-