Can H200 141GB SXM5 run Llama-3.2-3B-Instruct?

NVIDIA · 141 GB HBM3e · 4800 GB/s bandwidth · Meta · 3.2B · model ctx up to 128K

Yes — the H200 141GB SXM5 (141 GB HBM3e) can run Llama-3.2-3B-Instruct. At Q4 with the default 8K context it needs ≈ 3.4 GB VRAM (weights 1.76 GB + KV cache 0.64 GB + 1 GB runtime overhead), which fits within 141 GB. Decode at Q4/8K: ≈ 954.5 tok/s (estimated, batch 1). FP16 (≈ 8.04 GB) also fits, at ≈ 262.5 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	3.08 GB	Yes	954.5 est.
Q4	8K default	3.4 GB	Yes	954.5 est.
Q4	32K	5.32 GB	Yes	954.5 est.
FP16	4K	7.72 GB	Yes	262.5 est.
FP16	8K default	8.04 GB	Yes	262.5 est.
FP16	32K	9.96 GB	Yes	262.5 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	H200 141GB SXM5 VRAM
Q4	1.76 GB	0.64 GB	1 GB	3.4 GB	141 GB
FP16	6.4 GB	0.64 GB	1 GB	8.04 GB	141 GB

Other GPUs that run Llama-3.2-3B-Instruct

• B200 192GB SXM — ≈1590.9 tok/s Q4 est.
• MI300X 192GB — ≈1054.0 tok/s Q4 est.
• H100 80GB SXM5 — ≈666.2 tok/s Q4 est.
• Gaudi 3 128GB — ≈651.5 tok/s Q4 est.
• A100 80GB SXM4 — ≈405.5 tok/s Q4 est.
• RTX 5090 32GB — ≈356.4 tok/s Q4 est.
• RTX 4090 24GB — ≈200.5 tok/s Q4 est.
• RTX 4090D 24GB (China) — ≈200.5 tok/s Q4 est.

All GPUs for Llama-3.2-3B-Instruct →

Other models for the H200 141GB SXM5

• Qwen3-0.6B — ≈3818.2 tok/s Q4 est.
• gemma-3-1b-it — ≈3054.5 tok/s Q4 est.
• Llama-3.2-1B-Instruct — ≈2545.5 tok/s Q4 est.
• Qwen3-1.7B — ≈1527.3 tok/s Q4 est.
• Qwen3-30B-A3B — ≈1018.2 tok/s Q4 est.
• Qwen3-Coder-30B-A3B-Instruct — ≈1018.2 tok/s Q4 est.
• GLM-4.7-Flash — ≈1018.2 tok/s Q4 est.
• Qwen3-30B-A3B-Instruct-2507 — ≈1018.2 tok/s Q4 est.

All models on the H200 141GB SXM5 →