← Back to context Comment by re-thc 4 months ago Mistral Small 4 is already announced. 2 comments re-thc Reply androiddrew 4 months ago MOE but 120B range. Man I wish it was an 80B. I have 2 GPUs with 62Gib of usable VRAM. A 4bit 80B gives me some context window, but 120B puts me into system RAM Aerroon 4 months ago Either some q3 or since it's a MoE, maybe a REAP version of q4 might work (or could be terrible, I'm not sure about REAP'd models).
androiddrew 4 months ago MOE but 120B range. Man I wish it was an 80B. I have 2 GPUs with 62Gib of usable VRAM. A 4bit 80B gives me some context window, but 120B puts me into system RAM Aerroon 4 months ago Either some q3 or since it's a MoE, maybe a REAP version of q4 might work (or could be terrible, I'm not sure about REAP'd models).
Aerroon 4 months ago Either some q3 or since it's a MoE, maybe a REAP version of q4 might work (or could be terrible, I'm not sure about REAP'd models).
MOE but 120B range. Man I wish it was an 80B. I have 2 GPUs with 62Gib of usable VRAM. A 4bit 80B gives me some context window, but 120B puts me into system RAM
Either some q3 or since it's a MoE, maybe a REAP version of q4 might work (or could be terrible, I'm not sure about REAP'd models).