- Services
MiMo-V2.6-Pro-RL is the flagship open-weights checkpoint of the MiMo-V2.6 series from the Xiaomi MiMo Team, released under the MIT license. It is a sparse mixture-of-experts model with 1.02T total and 42B activated parameters, a 1M token context window, and native text, image, video and audio input. Xiaomi trained it with one mixed reinforcement learning run spanning coding, general agents, visual and cybersecurity tasks, plus multi-prefix multi-teacher on-policy distillation. It can be served with SGLang or vLLM and is also offered through the Xiaomi MiMo API platform and OpenRouter.
A solid 1024.22B-parameter MoE language model from Xiaomi MiMo. A pragmatic middle-ground choice when you need open weights without a flagship-sized footprint. Newly released, so production-readiness is still being shaken out.
Generated from this model’s benchmarks and ranking signals. Editor reviews refine it over time.
Access model weights, configuration files, and documentation.
No benchmark data available for this model yet.
See how different quantization levels affect VRAM requirements and quality for this model.
| Format | VRAM Required | Quality | |
|---|---|---|---|
| Q2_K | 352.0 GB | Low | |
| Q4_K_MRecommended | 360.9 GB | Good | |
| Q5_K_M | 365.1 GB | Very Good | |
| Q6_K | 370.1 GB | Excellent | |
| Q8_0 | 380.6 GB | Near Perfect | |
| FP16 | 420.5 GB | Full |
The top devices for this model at 4-bit, ranked by fit and speed.
| Device | Grade | Speed | VRAM |
|---|---|---|---|
| ASUS ExpertCenter Pro ET900N G3ASUS | AA | 15.8 tok/s | 360.9 GB |
| Dell Pro Max with GB300Dell | AA | 15.8 tok/s | 360.9 GB |
| HP ZGX Fury AI StationHP | AA | 15.8 tok/s | 360.9 GB |
| MSI XpertStation WS300MSI | AA | 15.8 tok/s | 360.9 GB |
| SuperMicro Super AI StationSuperMicro | AA | 15.8 tok/s | 360.9 GB |
Energy cost on Apple M3 Ultra (32-core CPU, 80-core GPU) (~1.8 tok/s, Q4_K_M) vs flagship API pricing.
| Source | Cost per 1M tokens |
|---|---|
Local (energy only)MiMo-V2.6-Pro-RL on Apple M3 Ultra (32-core CPU, 80-core GPU) · ~1.8 tok/s · 160W | $2.92 |
GPT-6 SolOpenAI · in $2.00 · out $10.00 | $4.40 |
Claude Opus 5.5Anthropic · in $4.00 · out $20.00 | $8.80 |
Gemini 3.5 FlashGoogle · in $1.50 · out $9.00 | $3.75 |
Grok 4.5xAI · in $2.00 · out $6.00 | $3.20 |
API prices blended at 70% input / 30% output.
Hardware amortisation not included. Run the full ROI calculator for payback math.
Cheapest current cloud rentals with at least 361 GB VRAM, refreshed hourly.
No current rental listing covers this model’s VRAM requirement on the providers we track.
Explore the Provider
Aggregate stats, leaderboard, release timeline, and benchmark coverage across every Xiaomi MiMo model we track.
Check which of your devices can run this model and how fast.
Compare hosted per-token prices before you commit to local hardware.
Break-even math for self-hosting, renting a GPU, or paying per token.
Live status for the hosted APIs you might use instead of running this locally.
View on Hugging Face