← AI Hashrate

Can B200 192GB SXM run Qwen3-0.6B?

NVIDIA · 192 GB HBM3e · 8000 GB/s bandwidth · Alibaba · 0.8B · model ctx up to 40K

Yes — the B200 192GB SXM (192 GB HBM3e) can run Qwen3-0.6B. At Q4 with the default 8K context it needs ≈ 1.6 GB VRAM (weights 0.44 GB + KV cache 0.16 GB + 1 GB runtime overhead), which fits within 192 GB. Decode at Q4/8K: ≈ 5000 tok/s (estimated, batch 1). FP16 (≈ 2.76 GB) also fits, at ≈ 1750.0 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)
Q44K1.52 GBYes5000 est.
Q48K default1.6 GBYes5000 est.
Q432K2.08 GBYes5000 est.
FP164K2.68 GBYes1750.0 est.
FP168K default2.76 GBYes1750.0 est.
FP1632K3.24 GBYes1750.0 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
Q40.44 GB0.16 GB1 GB1.6 GB192 GB
FP161.6 GB0.16 GB1 GB2.76 GB192 GB

Other GPUs that run Qwen3-0.6B

All GPUs for Qwen3-0.6B →

Other models for the B200 192GB SXM

All models on the B200 192GB SXM →