Can Gaudi 3 128GB run MiMo-V2.5?

Intel · 128 GB HBM2e · 3276 GB/s bandwidth · Xiaomi · 310.0B (active 15.0B) · MoE · model ctx up to 1024K

No — MiMo-V2.5 at Q4 needs ≈ 173.0 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: ≈ 213.7 tok/s (estimated, batch 1). FP16 needs ≈ 624.0 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	173.0 GB	No	217.4 est.
Q4	8K default	174.5 GB	No	213.7 est.
Q4	32K	183.5 GB	No	193.2 est.
FP16	4K	622.5 GB	No	—
FP16	8K default	624.0 GB	No	—
FP16	32K	633.0 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	170.5 GB	3.0 GB	1 GB	174.5 GB	128 GB
FP16	620.0 GB	3.0 GB	1 GB	624.0 GB	128 GB

Other GPUs that run MiMo-V2.5

• B200 192GB SXM — ≈339.4 tok/s Q4 est.
• MI300X 192GB — ≈224.8 tok/s Q4 est.
• Mac Studio M2 Ultra 192GB — ≈33.9 tok/s Q4 est.

All GPUs for MiMo-V2.5 →

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 →