AmpereComputing/qwen-3-a3b-30b-gguf
31B
•
Updated
•
41
Qwen 3
Ampere's quantization formats (Q4_K_4 / Q8R16) require Ampere optimized llama.cpp available here: https://hub.docker.com/r/amperecomputingai/llama.cpp
-
-
AmpereComputing/qwen-3-a22b-235b-gguf
235B • Updated • 155 -
AmpereComputing/qwen-3-coder-a35b-480b-instruct-gguf
480B • Updated • 6 -
AmpereComputing/qwen-3-0.6b-gguf
0.8B • Updated • 5 -
AmpereComputing/qwen-3-1.7b-gguf
2B • Updated • 6 • 1 -
AmpereComputing/qwen-3-4b-gguf
4B • Updated • 9 • 1 -
AmpereComputing/qwen-3-8b-gguf
8B • Updated • 6 -
AmpereComputing/qwen-3-14b-gguf
15B • Updated • 7 -
AmpereComputing/qwen-3-32b-gguf
33B • Updated • 7