Can MI300X 192GB run NVIDIA-Nemotron-3-Super-120B-A12B-BF16?

AMD · 192 GB HBM3 · 5300 GB/s bandwidth · NVIDIA · 120.0B (active 12.0B) · MoE · model ctx up to 256K

Yes — the MI300X 192GB (192 GB HBM3) can run NVIDIA-Nemotron-3-Super-120B-A12B-BF16. At Q4 with the default 8K context it needs ≈ 69.4 GB VRAM (weights 66.0 GB + KV cache 2.4 GB + 1 GB runtime overhead), which fits within 192 GB. Decode at Q4/8K: ≈ 281.1 tok/s (estimated, batch 1). FP16 needs ≈ 243.4 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	68.2 GB	Yes	281.1 est.
Q4	8K default	69.4 GB	Yes	281.1 est.
Q4	32K	76.6 GB	Yes	281.1 est.
FP16	4K	242.2 GB	No	138.8 est.
FP16	8K default	243.4 GB	No	137.4 est.
FP16	32K	250.6 GB	No	129.6 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	MI300X 192GB VRAM
Q4	66.0 GB	2.4 GB	1 GB	69.4 GB	192 GB
FP16	240.0 GB	2.4 GB	1 GB	243.4 GB	192 GB

Other GPUs that run NVIDIA-Nemotron-3-Super-120B-A12B-BF16

• B200 192GB SXM — ≈424.2 tok/s Q4 est.
• H200 141GB SXM5 — ≈254.5 tok/s Q4 est.
• H100 80GB SXM5 — ≈177.7 tok/s Q4 est.
• Gaudi 3 128GB — ≈173.7 tok/s Q4 est.
• A100 80GB SXM4 — ≈108.1 tok/s Q4 est.
• Mac Studio M3 Ultra 96GB — ≈43.4 tok/s Q4 est.
• Mac Studio M2 Ultra 192GB — ≈42.4 tok/s Q4 est.
• MacBook Pro M4 Max 128GB — ≈29.0 tok/s Q4 est.

All GPUs for NVIDIA-Nemotron-3-Super-120B-A12B-BF16 →

Other models for the MI300X 192GB

• MiniCPM5-1B — ≈3122.9 tok/s Q4 est.
• Qwen3.5-2B — ≈1686.4 tok/s Q4 est.
• GLM-4.7-Flash — ≈1124.2 tok/s Q4 est.
• Qwen3-30B-A3B-Instruct-2507 — ≈1124.2 tok/s Q4 est.
• Qwen3-Next-80B-A3B-Instruct — ≈1124.2 tok/s Q4 est.
• Qwen3-Coder-Next — ≈1124.2 tok/s Q4 est.
• Qwen3.5-35B-A3B — ≈1124.2 tok/s Q4 est.
• Qwen3.6-35B-A3B — ≈1124.2 tok/s Q4 est.

All models on the MI300X 192GB →