Can B200 192GB SXM run Qwen3-Coder-Next?

NVIDIA · 192 GB HBM3e · 8000 GB/s bandwidth · Alibaba · 79.7B (active 3B) · MoE · model ctx up to 256K

Yes — the B200 192GB SXM (192 GB HBM3e) can run Qwen3-Coder-Next. At Q4 with the default 8K context it needs ≈ 45.44 GB VRAM (weights 43.84 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 (≈ 161.0 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	45.14 GB	Yes	1697.0 est.
Q4	8K default	45.44 GB	Yes	1697.0 est.
Q4	32K	47.24 GB	Yes	1697.0 est.
FP16	4K	160.7 GB	Yes	466.7 est.
FP16	8K default	161.0 GB	Yes	466.7 est.
FP16	32K	162.8 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	43.84 GB	0.6 GB	1 GB	45.44 GB	192 GB
FP16	159.4 GB	0.6 GB	1 GB	161.0 GB	192 GB

Other GPUs that run Qwen3-Coder-Next

• 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 6000 Ada 48GB — ≈203.6 tok/s Q4 est.
• L40S 48GB — ≈183.3 tok/s Q4 est.
• Mac Studio M3 Ultra 96GB — ≈173.7 tok/s Q4 est.

All GPUs for Qwen3-Coder-Next →

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 →