MiMo-V2-Pro 1T+ — VRAM, Speed & Local Setup

Written by Jakub Rusinowski · Last updated March 10, 2026

Model library → MiMo-V2-Pro → MiMo-V2-Pro 1T+

Xiaomi's frontier 1T+ MoE model, revealed as the anonymous 'Hunter Alpha' submission in March 2026. With ~42B active parameters per token it delivers strong agentic and coding performance. Context window up to 1M tokens (tiered pricing). Datacenter-only self-hosting (~550 GB at Q4); accessible via API at $2–6/1M tokens.

MiMo-V2-Pro 1T+ needs about 605 GB of VRAM at Q4_K_M — quantized weights plus framework overhead, before any KV cache. On Apple Silicon that figure comes out of unified memory.

Specifications

Parameters	1T+ (42B active)
Context window	1,000,000
Architecture	Mixture-of-Experts
Provider	Xiaomi
Licence	Open-weight
Specified at	Q4_K_M
System RAM	1024 GB
Record updated	2026-03-10

Licence

Custom Open-Weight — commercial use permitted. Weights are downloadable and commercial use is permitted, subject to the licence’s acceptable-use terms.

VRAM and Speed by Quantization

Modelled on a reference NVIDIA RTX 4090 (24 GB), with no KV cache (this record has no published architecture). Speed figures are ESTIMATES from the memory-bandwidth roofline described on the methodology page, not benchmarks we ran — rows marked measured come from published or reader-submitted runs. VRAM here includes the KV cache, so it reads higher than the headline figure above, which does not.

Quant	Weights	VRAM needed	Est. speed	Fit on 24 GB
Q2_K	328.8 GB	329.6 GB	—	Won't fit
Q3_K_M	426.3 GB	427.1 GB	—	Won't fit
Q4_K_M	603.8 GB	604.5 GB	—	Won't fit
Q5_K_M	708.8 GB	709.5 GB	—	Won't fit
Q6_K	820.0 GB	820.8 GB	—	Won't fit
Q8_0	1062.5 GB	1063.3 GB	—	Won't fit
F16	2000.0 GB	2000.8 GB	—	Won't fit

Want the memory numbers alone, at every quantization level and your own context length? Use the MiMo-V2-Pro 1T+ VRAM calculator.

Deploy in the Cloud NowRunPod

or compare on Vast.ai

As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.

How to Run MiMo-V2-Pro 1T+

Install Ollama, then run:

ollama run mimo-v2-pro

Weights on Hugging Face: XiaomiMiMo/MiMo-V2-Pro.

Best for: agentic tasks, coding, enterprise, cloud api.

Can I Run MiMo-V2-Pro 1T+ on My GPU?

MiMo-V2-Pro on Apple M3 Ultra

MiMo-V2-Pro 1T+ — Frequently Asked Questions

How much VRAM does MiMo-V2-Pro 1T+ need?

About 605 GB at Q4_K_M — quantized weights plus framework overhead, before any KV cache. The cache grows with context length and is added on top; the table above folds it in. Apple Silicon counts unified memory toward the same figure.

Does MiMo-V2-Pro 1T+ run on an RTX 4090 (24 GB)?

No. MiMo-V2-Pro 1T+ needs about 605 GB at Q4_K_M, more than a single RTX 4090's 24 GB. It needs a larger card, several GPUs, or Apple Silicon with enough unified memory — or it runs with part of the weights offloaded to system RAM, which is much slower.

How do I run MiMo-V2-Pro 1T+ locally?

Install Ollama and run `ollama run mimo-v2-pro`. That pulls the weights and starts a local OpenAI-compatible endpoint; after the download nothing leaves the machine.

← All MiMo-V2-Pro models | VRAM calculator | Check your own hardware