Xiaomi1T/42B active~605 GB VRAM at Q4_K_M

MiMo-V2.5-Pro 1T — VRAM, speed & local setup

Written by Jakub Rusinowski · Last updated September 6, 2026

The flagship: 1 trillion total, 42B active per token, MIT, 1M context. Matches frontier coding models on published comparisons at a licence that imposes no revenue threshold. Datacenter-class to self-host at about 605 GB at Q4_K_M.

MiMo-V2.5-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.

Logic94

Creative91

Coding95

VRAM and speed by quantization

Quoted against NVIDIA RTX 4090 (24 GB). Weights plus overhead only: this model's architecture is unpublished, so no KV cache is added.

Quant	VRAM	Speed (est.)	Fit
Q2_K 2.63 bpw	329.6 GB	—	Too big
Q3_K_M 3.41 bpw	427.1 GB	—	Too big
Q4_K_M 4.83 bpw	604.6 GB	—	Too big
Q5_K_M 5.67 bpw	709.6 GB	—	Too big
Q6_K 6.56 bpw	820.8 GB	—	Too big
Q8_0 8.50 bpw	1063.3 GB	—	Too big
F16 16.00 bpw	2000.8 GB	—	Too big

Black marker = usable memory on the NVIDIA RTX 4090 (24 GB). Estimates from the memory-bandwidth roofline on the methodology page. MiMo-V2.5-Pro 1T VRAM calculator →

Get MiMo-V2.5-Pro 1T running

MiMo-V2.5-Pro 1T is not practical on a single consumer GPU: it needs about 604.6 GB at Q4_K_M, more than any single device in our catalogue holds with headroom. How multi-GPU inference works, or rent a multi-GPU server by the hour:

Deploy in the cloud now RunPod

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-V2.5-Pro 1T

Install Ollama, then run:

$ollama run mimo-v2-5

Weights on Hugging Face: XiaomiMiMo/MiMo-V2.5-Pro ↗

Specifications

Verified — Checked against the primary source — the model card or the vendor spec page — and corroborated by a second independent source.

Parameters: 1 Trillion (42B active)
Context window: 1,000,000
Architecture: Mixture-of-Experts
Provider: Xiaomi
Licence: MIT
Practical deployment: Private cloud / datacenter cluster
Specified at: Q4_K_M
System RAM: 768 GB
Record updated: 2026-09-06

LicenceMITCommercial use permitted

Commercial use permitted. No usage restrictions beyond attribution.

Quality and use cases

Scores as published by the model’s authors or an independent evaluator — quality, not throughput, and not measured by us.

Best forcodingagentic taskslong contextenterprise

Can I run MiMo-V2.5-Pro 1T on my GPU?

Other MiMo-V2.5 sizes

MiMo-V2.5 310B~188 GB at Q4_K_M

MiMo-V2.5-Pro 1T — frequently asked questions

How much VRAM does MiMo-V2.5-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-V2.5-Pro 1T run on an RTX 4090 (24 GB)?

No. MiMo-V2.5-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-V2.5-Pro 1T locally?

Install Ollama and run `ollama run mimo-v2-5`. That pulls the weights and starts a local OpenAI-compatible endpoint; after the download nothing leaves the machine.

What other sizes does MiMo-V2.5 come in?

MiMo-V2.5 310B (188 GB), MiMo-V2.5-Pro 1T (605 GB). Every size shares the family's training and licence; the larger ones score higher and need proportionally more memory.