What's the best open weight Mixture-of-Experts LLM for coding that fits in less than 60GB of RAM?
I think MoE might be necessary to get reasonably interactive speeds on the hardware I have access to - I want something faster than 12 tokens/second
I think MoE might be necessary to get reasonably interactive speeds on the hardware I have access to - I want something faster than 12 tokens/second
127 7 2 285 50.3K 139
Kyle Daigle
Mistral AI
Claude
Thomas H. Ptacek
WeAreDevelopers
Gergely Orosz