← AI Hashrate 中文

Can Arc Pro B70 32GB run Qwen3.5-9B?

Intel · 32 GB GDDR6 · 608 GB/s bandwidth · Alibaba · 8.95B · model ctx up to 256K

SS · ExcellentComposite score: VRAM headroom × 0.5 + tok/s speed × 0.5. Q4 @ 8K context.
ONEAPI

Yes — the Arc Pro B70 32GB (32 GB GDDR6) can run Qwen3.5-9B. At Q4 with the default 8K context it needs ≈ 6.15 GB VRAM (weights 4.92 GB + KV cache 0.22 GB + 1 GB runtime overhead), which fits within 32 GB. Decode at Q4/8K: ≈ 43.2 tok/s (estimated, batch 1). FP16 (≈ 19.12 GB) also fits, at ≈ 11.9 tok/s (estimated). 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

QuantContextVRAM neededFits?tok/s (decode)
Q44K6.03 GBYes43.2 est.
Q48K default6.15 GBYes43.2 est.
Q432K6.82 GBYes43.2 est.
FP164K19.01 GBYes11.9 est.
FP168K default19.12 GBYes11.9 est.
FP1632K19.79 GBYes11.9 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).

VRAM breakdown at 8K context

QuantWeightsKV cacheOverheadTotal neededArc Pro B70 32GB VRAM
Q44.92 GB0.22 GB1 GB6.15 GB32 GB
FP1617.9 GB0.22 GB1 GB19.12 GB32 GB

Other GPUs that run Qwen3.5-9B

All GPUs for Qwen3.5-9B →

Other models for the Arc Pro B70 32GB

All models on the Arc Pro B70 32GB →