← AI Hashrate

Can B200 192GB SXM run Qwen3.5-2B?

NVIDIA · 192 GB HBM3e · 8000 GB/s bandwidth · Alibaba · 2.0B · model ctx up to 256K

Yes — the B200 192GB SXM (192 GB HBM3e) can run Qwen3.5-2B. At Q4 with the default 8K context it needs ≈ 2.5 GB VRAM (weights 1.1 GB + KV cache 0.4 GB + 1 GB runtime overhead), which fits within 192 GB. Decode at Q4/8K: ≈ 2545.5 tok/s (estimated, batch 1). FP16 (≈ 5.4 GB) also fits, at ≈ 700.0 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)
Q44K2.3 GBYes2545.5 est.
Q48K default2.5 GBYes2545.5 est.
Q432K3.7 GBYes2545.5 est.
FP164K5.2 GBYes700.0 est.
FP168K default5.4 GBYes700.0 est.
FP1632K6.6 GBYes700.0 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 neededB200 192GB SXM VRAM
Q41.1 GB0.4 GB1 GB2.5 GB192 GB
FP164.0 GB0.4 GB1 GB5.4 GB192 GB

Other GPUs that run Qwen3.5-2B

All GPUs for Qwen3.5-2B →

Other models for the B200 192GB SXM

All models on the B200 192GB SXM →