Can Gaudi 3 128GB run MiniMax-M1?

Intel · 128 GB HBM2e · 3276 GB/s bandwidth · MiniMax · 456.1B (active 45.9B) · MoE · model ctx up to 1000K

No — MiniMax-M1 at Q4 needs ≈ 256.45 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: ≈ 31.2 tok/s (estimated, batch 1). FP16 needs ≈ 922.38 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	256.45 GB	No	32.3 est.
Q4	8K default	261.04 GB	No	31.2 est.
Q4	32K	288.58 GB	No	25.5 est.
FP16	4K	917.79 GB	No	—
FP16	8K default	922.38 GB	No	—
FP16	32K	949.92 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	250.86 GB	9.18 GB	1 GB	261.04 GB	128 GB
FP16	912.2 GB	9.18 GB	1 GB	922.38 GB	128 GB

Other GPUs that run MiniMax-M1

No catalog GPU fully fits MiniMax-M1 at Q4/8K — see the model page for offload estimates.

All GPUs for MiniMax-M1 →

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 →