| ▲ | Aurornis 2 hours ago | |
> As this is a dense model and it's pretty sizable, 4-bit quantization can be nearly lossless The 4-bit quants are far from lossless. The effects show up more on longer context problems. > You can probably even go FP8 with 5090 (though there will be tradeoffs) You cannot run these models at 8-bit on a 32GB card because you need space for context. Typically it would be Q5 on a 32GB card to fit context lengths needed for anything other than short answers. | ||
| ▲ | alex7o 8 minutes ago | parent | next [-] | |
Turboquant on 4bit helps a lot as well for keeping context in vram, but int4 is definitely not lossless. But it all depends for some people this is sufficient | ||
| ▲ | ekojs 2 hours ago | parent | prev [-] | |
> You cannot run these models at 8-bit on a 32GB card because you need space for context You probably can actually. Not saying that it would be ideal but it can fit entirely in VRAM (if you make sure to quantize the attention layers). KV cache quantization and not loading the vision tower would help quite a bit. Not ideal for long context, but it should be very much possible. I addressed the lossless claim in another reply but I guess it really depends on what the model is used for. For my usecases, it's nearly lossless I'd say. | ||