Can B200 192GB SXM run GLM-4.7-Flash?

NVIDIA · 192 GB HBM3e · 8000 GB/s bandwidth · Z.ai · 31.2B (active 3B) · MoE · model ctx up to 198K

Yes — the B200 192GB SXM (192 GB HBM3e) can run GLM-4.7-Flash. At Q4 with the default 8K context it needs ≈ 18.76 GB VRAM (weights 17.16 GB + KV cache 0.6 GB + 1 GB runtime overhead), which fits within 192 GB. Decode at Q4/8K: ≈ 1697.0 tok/s (estimated, batch 1). FP16 (≈ 64.0 GB) also fits, at ≈ 466.7 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

Quant	Context	VRAM needed	Fits?	tok/s (decode)
Q4	4K	18.46 GB	Yes	1697.0 est.
Q4	8K default	18.76 GB	Yes	1697.0 est.
Q4	32K	20.56 GB	Yes	1697.0 est.
FP16	4K	63.7 GB	Yes	466.7 est.
FP16	8K default	64.0 GB	Yes	466.7 est.
FP16	32K	65.8 GB	Yes	466.7 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	17.16 GB	0.6 GB	1 GB	18.76 GB	192 GB
FP16	62.4 GB	0.6 GB	1 GB	64.0 GB	192 GB

Other GPUs that run GLM-4.7-Flash

• MI300X 192GB — ≈1124.2 tok/s Q4 est.
• H200 141GB SXM5 — ≈1018.2 tok/s Q4 est.
• H100 80GB SXM5 — ≈710.6 tok/s Q4 est.
• Gaudi 3 128GB — ≈694.9 tok/s Q4 est.
• A100 80GB SXM4 — ≈432.5 tok/s Q4 est.
• RTX 5090 32GB — ≈380.1 tok/s Q4 est.
• RTX 4090 24GB — ≈213.8 tok/s Q4 est.
• RTX 4090D 24GB (China) — ≈213.8 tok/s Q4 est.

All GPUs for GLM-4.7-Flash →

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.
• Qwen3-30B-A3B-Instruct-2507 — ≈1697.0 tok/s Q4 est.
• Qwen3-Next-80B-A3B-Instruct — ≈1697.0 tok/s Q4 est.

All models on the B200 192GB SXM →