Can Gaudi 3 128GB run NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4?

Intel · 128 GB HBM2e · 3276 GB/s bandwidth · NVIDIA · 550.0B (active 55.0B) · MoE · model ctx up to 256K

No — NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4 at Q4 needs ≈ 309.0 GB even at 4K context, beyond the Gaudi 3 128GB's 128 GB HBM2e. It would only run with heavy CPU/disk offload. Decode at Q4/8K: ≈ 17.9 tok/s (estimated, batch 1). FP16 needs ≈ 1112.0 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	309.0 GB	No	18.6 est.
Q4	8K default	314.5 GB	No	17.9 est.
Q4	32K	347.5 GB	No	14.7 est.
FP16	4K	1106.5 GB	No	—
FP16	8K default	1112.0 GB	No	—
FP16	32K	1145.0 GB	No	—

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	Gaudi 3 128GB VRAM
Q4	302.5 GB	11.0 GB	1 GB	314.5 GB	128 GB
FP16	1100.0 GB	11.0 GB	1 GB	1112.0 GB	128 GB

Other GPUs that run NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4

No catalog GPU fully fits NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4 at Q4/8K — see the model page for offload estimates.

All GPUs for NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4 →

Other models for the Gaudi 3 128GB

• MiniCPM5-1B — ≈1930.3 tok/s Q4 est.
• Qwen3.5-2B — ≈1042.4 tok/s Q4 est.
• GLM-4.7-Flash — ≈694.9 tok/s Q4 est.
• Qwen3-30B-A3B-Instruct-2507 — ≈694.9 tok/s Q4 est.
• Qwen3-Next-80B-A3B-Instruct — ≈694.9 tok/s Q4 est.
• Qwen3-Coder-Next — ≈694.9 tok/s Q4 est.
• Qwen3.5-35B-A3B — ≈694.9 tok/s Q4 est.
• Qwen3.6-35B-A3B — ≈694.9 tok/s Q4 est.

All models on the Gaudi 3 128GB →