Muse Glimmer 30B quantized with Intel AutoRound at a 3.5-bit target and packed with llm-compressor, tested on vLLM.
Resource · Local & open models· ♥ 3
1 build · page 1 of 1
Entries matching “autoround”
1 build · page 1 of 1
Muse Glimmer 30B quantized with Intel AutoRound at a 3.5-bit target and packed with llm-compressor, tested on vLLM.
Resource · Local & open models· ♥ 3
ChatForm
Tgmlabs