Can L40S 48GB run MiMo-V2.5?

NVIDIA · 48 GB GDDR6 · 864 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 L40S 48GB's 48 GB GDDR6. It would only run with heavy CPU/disk offload. Decode at Q4/8K: ≈ 7.9 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	8.1 est.
Q4	8K default	174.5 GB	No	7.9 est.
Q4	32K	183.5 GB	No	7.2 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	L40S 48GB VRAM
Q4	170.5 GB	3.0 GB	1 GB	174.5 GB	48 GB
FP16	620.0 GB	3.0 GB	1 GB	624.0 GB	48 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 L40S 48GB

• MiniCPM5-1B — ≈509.1 tok/s Q4 est.
• Qwen3.5-2B — ≈274.9 tok/s Q4 est.
• GLM-4.7-Flash — ≈183.3 tok/s Q4 est.
• Qwen3-30B-A3B-Instruct-2507 — ≈183.3 tok/s Q4 est.
• Qwen3-Coder-Next — ≈183.3 tok/s Q4 est.
• Qwen3.5-35B-A3B — ≈183.3 tok/s Q4 est.
• Qwen3.6-35B-A3B — ≈183.3 tok/s Q4 est.
• Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16 — ≈183.3 tok/s Q4 est.

All models on the L40S 48GB →