Can B200 192GB SXM run GLM-4.5?

NVIDIA · 192 GB HBM3e · 8000 GB/s bandwidth · Z.ai · 358.3B (active 32B) · MoE · model ctx up to 128K

No — GLM-4.5 at Q4 needs ≈ 201.27 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: ≈ 400.8 tok/s (estimated, batch 1). FP16 needs ≈ 724.0 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	201.27 GB	No	413.6 est.
Q4	8K default	204.47 GB	No	400.8 est.
Q4	32K	223.67 GB	No	334.9 est.
FP16	4K	720.8 GB	No	8.9 est.
FP16	8K default	724.0 GB	No	8.8 est.
FP16	32K	743.2 GB	No	8.3 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	197.07 GB	6.4 GB	1 GB	204.47 GB	192 GB
FP16	716.6 GB	6.4 GB	1 GB	724.0 GB	192 GB

Other GPUs that run GLM-4.5

No catalog GPU fully fits GLM-4.5 at Q4/8K — see the model page for offload estimates.

All GPUs for GLM-4.5 →

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 →