Can I run a fp8 quant with 96gb VRAM?
Only VRAM? Unlikely unless you can also load the whole model into regular RAM. The previous 3.5 release was 250gb at BF16, so FP8 would likely be around 125gb. Your best best is FP4/Q4.
alt Hacker News
Only VRAM? Unlikely unless you can also load the whole model into regular RAM. The previous 3.5 release was 250gb at BF16, so FP8 would likely be around 125gb. Your best best is FP4/Q4.