Can Gaudi 3 128GB run Qwen3-Coder-480B-A35B-Instruct?

Intel · 128 GB HBM2e · 3276 GB/s bandwidth · Alibaba · 480.2B (active 35B) · MoE · model ctx up to 256K

No — Qwen3-Coder-480B-A35B-Instruct at Q4 needs ≈ 268.61 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: ≈ 37.7 tok/s (estimated, batch 1). FP16 needs ≈ 968.4 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	268.61 GB	No	38.6 est.
Q4	8K default	272.11 GB	No	37.7 est.
Q4	32K	293.11 GB	No	32.5 est.
FP16	4K	964.9 GB	No	—
FP16	8K default	968.4 GB	No	—
FP16	32K	989.4 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	264.11 GB	7.0 GB	1 GB	272.11 GB	128 GB
FP16	960.4 GB	7.0 GB	1 GB	968.4 GB	128 GB

Other GPUs that run Qwen3-Coder-480B-A35B-Instruct

No catalog GPU fully fits Qwen3-Coder-480B-A35B-Instruct at Q4/8K — see the model page for offload estimates.

All GPUs for Qwen3-Coder-480B-A35B-Instruct →

Other models for the Gaudi 3 128GB

• Qwen3-0.6B — ≈2605.9 tok/s Q4 est.
• gemma-3-1b-it — ≈2084.7 tok/s Q4 est.
• Llama-3.2-1B-Instruct — ≈1737.3 tok/s Q4 est.
• Qwen3-1.7B — ≈1042.4 tok/s Q4 est.
• Qwen3-30B-A3B — ≈694.9 tok/s Q4 est.
• Qwen3-Coder-30B-A3B-Instruct — ≈694.9 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.

All models on the Gaudi 3 128GB →