Estimates from memory-bandwidth formula; rows marked "measured" override. Methodology.
Fit & speed by quant and context
Quant
Context
VRAM needed
Fits?
tok/s (decode)
Q4
4K
171.69 GB
Yes
339.4±est.
Q4
8K default
171.88 GB
Yes
339.4±est.
Q4
32K
173.0 GB
Yes
339.4±est.
FP16
4K
621.19 GB
No
25.5±est.
FP16
8K default
621.38 GB
No
25.5±est.
FP16
32K
622.5 GB
No
25.4±est.
Fits = weights + KV(ctx) + 1 GB overhead ≤ 95% of VRAM. Measured anchors are context-agnostic; the fit verdict is recomputed per context. A missing tok/s means the model is far beyond this card (offload-only territory).