MiMo-V2-Pro 1T+ — VRAM, speed & local setup
Written by Jakub Rusinowski · Last updated
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.
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 Weights plus overhead only: this model's architecture is unpublished, so no KV cache is added.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 | Memory | 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-Pro 1T+ VRAM calculator →
Get MiMo-V2-Pro 1T+ running
MiMo-V2-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:
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-proSpecifications
Preview — The model is released, but these specs are thin or rest on a single source. Individual fields may be wrong.
Preview — The model is released, but these specs are thin or rest on a single source. Individual fields may be wrong.
- Parameters
- 1T+ (42B active)
- Context window
- 1,000,000
- Architecture
- Mixture-of-Experts
- Provider
- Xiaomi
- Licence
- Open-weight
- Practical deployment
- Private cloud / datacenter cluster
- Specified at
- Q4_K_M
- System RAM
- 1024 GB
- Record updated
- 2026-03-10
Weights are downloadable and commercial use is permitted, subject to the licence’s acceptable-use terms.
Quality and use cases
Scores as published by the model’s authors or an independent evaluator — quality, not throughput, and not measured by us.
Can I run MiMo-V2-Pro 1T+ on my GPU?
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.