Yes — the Arc Pro B70 32GB (32 GB GDDR6) can run Qwen3.6-27B. At Q4 with the default 8K context it needs ≈ 16.98 GB VRAM (weights 15.29 GB + KV cache 0.7 GB + 1 GB runtime overhead), which fits within 32 GB. Decode at Q4/8K: ≈ 13.9 tok/s (estimated, batch 1). FP16 needs ≈ 57.3 GB — does not fit on this card. Estimates come from memory-bandwidth math; rows tagged measured override estimates. Relative ranking is more reliable than absolute tok/s. Methodology.
Fit & speed by quant and context
Quant
Context
VRAM needed
Fits?
tok/s (decode)
Q4
4K
16.64 GB
Yes
13.9est.
Q4
8K default
16.98 GB
Yes
13.9est.
Q4
32K
19.07 GB
Yes
13.9est.
FP16
4K
56.95 GB
No
3.4est.
FP16
8K default
57.3 GB
No
3.4est.
FP16
32K
59.38 GB
No
3.2est.
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).