Can B200 192GB SXM run GLM-5.1?

NVIDIA · 192 GB HBM3e · 8000 GB/s bandwidth · Z.ai · 753.9B (active 40B) · MoE · model ctx up to 198K

No — GLM-5.1 at Q4 needs ≈ 419.65 GB even at 4K context, beyond the B200 192GB SXM's 192 GB HBM3e. It would only run with heavy CPU/disk offload. Decode at Q4/8K: ≈ 74.7 tok/s (estimated, batch 1). FP16 needs ≈ 1516.8 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	419.65 GB	No	76.1 est.
Q4	8K default	423.65 GB	No	74.7 est.
Q4	32K	447.65 GB	No	66.9 est.
FP16	4K	1512.8 GB	No	—
FP16	8K default	1516.8 GB	No	—
FP16	32K	1540.8 GB	No	—

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	414.65 GB	8.0 GB	1 GB	423.65 GB	192 GB
FP16	1507.8 GB	8.0 GB	1 GB	1516.8 GB	192 GB

Other GPUs that run GLM-5.1

No catalog GPU fully fits GLM-5.1 at Q4/8K — see the model page for offload estimates.

All GPUs for GLM-5.1 →

Other models for the B200 192GB SXM

• gemma-3-1b-it — ≈5000 tok/s Q4 est.
• Qwen3-0.6B — ≈5000 tok/s Q4 est.
• Llama-3.2-1B-Instruct — ≈4242.4 tok/s Q4 est.
• Qwen3-1.7B — ≈2545.5 tok/s Q4 est.
• Qwen3-30B-A3B — ≈1697.0 tok/s Q4 est.
• Qwen3-Coder-30B-A3B-Instruct — ≈1697.0 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.

All models on the B200 192GB SXM →