Can B200 192GB SXM run Hy3?

NVIDIA · 192 GB HBM3e · 8000 GB/s bandwidth · Tencent · 295.0B (active 21.0B) · MoE · model ctx up to 256K

Yes — the B200 192GB SXM (192 GB HBM3e) can run Hy3. At Q4 with the default 8K context it needs ≈ 167.45 GB VRAM (weights 162.25 GB + KV cache 4.2 GB + 1 GB runtime overhead), which fits within 192 GB. Decode at Q4/8K: ≈ 242.4 tok/s (estimated, batch 1). FP16 needs ≈ 595.2 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	165.35 GB	Yes	242.4 est.
Q4	8K default	167.45 GB	Yes	242.4 est.
Q4	32K	180.05 GB	Yes	242.4 est.
FP16	4K	593.1 GB	No	20.0 est.
FP16	8K default	595.2 GB	No	19.8 est.
FP16	32K	607.8 GB	No	19.0 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

Quant	Weights	KV cache	Overhead	Total needed	B200 192GB SXM VRAM
Q4	162.25 GB	4.2 GB	1 GB	167.45 GB	192 GB
FP16	590.0 GB	4.2 GB	1 GB	595.2 GB	192 GB

Other GPUs that run Hy3

• MI300X 192GB — ≈160.6 tok/s Q4 est.
• Mac Studio M2 Ultra 192GB — ≈24.2 tok/s Q4 est.

All GPUs for Hy3 →

Other models for the B200 192GB SXM

• MiniCPM5-1B — ≈4713.8 tok/s Q4 est.
• Qwen3.5-2B — ≈2545.5 tok/s Q4 est.
• GLM-4.7-Flash — ≈1697.0 tok/s Q4 est.
• Qwen3-30B-A3B-Instruct-2507 — ≈1697.0 tok/s Q4 est.
• Qwen3-Next-80B-A3B-Instruct — ≈1697.0 tok/s Q4 est.
• Qwen3-Coder-Next — ≈1697.0 tok/s Q4 est.
• Qwen3.5-35B-A3B — ≈1697.0 tok/s Q4 est.
• Qwen3.6-35B-A3B — ≈1697.0 tok/s Q4 est.

All models on the B200 192GB SXM →