Get the latest setups
Models/MiMo V2.6/MiMo V2.6 Pro RL
Text / XiaomiMiMo

MiMo V2.6 Pro RL

MiMo V2.6 Pro RL is the flagship checkpoint of the MiMo-V2.6 series, released under the MIT license and intended for text-generation and multimodal use. Its model card describes scaling reinforcement learning toward self-improvement and lists native omnimodal support (text, image, video, audio), long-context handling up to 1M tokens, mixed RL across coding, general agents, visual, and cybersecurity, and training methods including GRPO, groupwise agentic grading, aligned RL, and MOPD2. The repository tags include safetensors and text-generation.

EstimatedRepository opened Sep 21, 2026Source checked 9/23/2026Version: 73875d00
LOCALRENTED GPUOPEN WEIGHTS
Freshness 91 out of 100. Repository age: 24 days old, Sep 21, 2026. Measures age, not quality.
Popularity 69 out of 100. 99,548 downloads in 30 days; 728 lifetime likes. Checked Oct 15, 2026. Measures adoption, not quality.
What do these scores mean?

Two ways to compare models. Neither score measures answer quality, benchmark performance, or whether a model fits your machine.

Freshness · release age

A new release starts at 100. The score halves every 180 days: 100 × 2^(−age in days / 180). When the release date is unavailable, a repository date is a fallback—not proof of when the model was released. Missing dates stay unscored.

Check the date source
Popularity · adoption

Downloads over the past 30 days carry 80% of the score; lifetime likes carry 20%. Both use a logarithmic scale, capped at 10 million downloads and 100,000 likes. If likes are unavailable, downloads carry all the weight. Missing download statistics stay unscored.

round(80 × min(1, log10(1 + downloads) / 7) + 20 × min(1, log10(1 + likes) / 5))

Check the statistics source
Scores as of Oct 15, 2026. Statistics checked Oct 15, 2026. Statistics are marked for refresh after 72 hours.Full scoring method

At a glance

Parameters
1024.22B
Architecture
mimo_v2
Context length
1,048,576
License
mit
Software
SGLang, vLLM
View the model source
MY HARDWARE

Will it run on your machine?

Save your machine to see a personalized rating and its reasoning.

Add my hardware

Best for

  • Text generation and language tasks in English and Chinese.
  • Multimodal or vision-language inputs, including images and video, where supported by the model.
  • Long-context processing such as long repositories, tool traces, or multi-session agent runs.
  • Agentic tasks involving tool use and coding, as described in the training setup.
  • Audio-related work, based on the model card's omnimodal and audio tags.

Tradeoffs

  • The source only provides training and feature claims from the official model card; it does not independently establish performance or capability guarantees.
  • No numerical hardware requirements, compatibility details, or deployment constraints are specified in the supplied data.
  • The listed 1M-token long-context capability and omnimodal tags are model-card claims, not verified facts from the supplied source.
  • The provided text-generation pipeline and safetensors tags do not by themselves confirm support for every listed modality.
  • No testing, benchmarking, or purchase recommendation is claimed or implied by the source data.

Ways to run it

SGLang · Linux

Repository-specific command in publisher documentation; confirm dependencies and hardware in the source.

sglang serve --trust-remote-code --model-path XiaomiMiMo/MiMo-V2.6-Pro-RL --tp 16 --dp 2 --enable-dp-attention --mm-enable-dp-encoder --ep 16 --moe-a2a-backend deepep --moe-dense-tp-size 1 --mem-fraction-static 0.7 --max-running-requests 128 \
Official instructions

vLLM · Linux

Repository-specific command in publisher documentation; confirm dependencies and hardware in the source.

vllm serve XiaomiMiMo/MiMo-V2.6-Pro-RL --tensor-parallel-size 8 --trust-remote-code --gpu-memory-utilization 0.95 --max-model-len auto --reasoning-parser mimo --tool-call-parser mimo --enable-auto-tool-choice --generation-config vllm
Official instructions

Explore its uses

SAFETENSORSTEXT-GENERATION

Keep exploring

Text
Prism ML

Bonsai 2 · 27B

A compressed 27B-class reasoning model with publisher-provided GGUF packs and a dedicated llama.cpp fork for CUDA, Metal, and CPU.

Freshness 90 out of 100. Release age: 28 days old, Sep 17, 2026. Measures age, not quality.
Popularity 90 out of 100. 4,849,199 downloads in 30 days; 2,697 lifetime likes. Checked Oct 15, 2026. Measures adoption, not quality.
MODEL SIZE27.36B
LOCALRENTED GPU
Released Sep 17, 2026
Text
DeepSeek

DeepSeek V4.1 Flash

A multimodal reasoning model with a compressed key-value cache, published as open weights.

Freshness 87 out of 100. Repository age: 35 days old, Sep 10, 2026. Measures age, not quality.
Popularity 84 out of 100. 1,238,583 downloads in 30 days; 4,519 lifetime likes. Checked Oct 15, 2026. Measures adoption, not quality.
Arena Open Source Text: rank 5 of 225. Ranked model: deepseek-v4.1-flash-max. Export dated Oct 13, 2026. Source checked Oct 15, 2026. Human preference ranking, not hardware suitability.+3
LOCALRENTED GPU
Repository opened Sep 10, 2026
Text
Qwen

Qwen3.8

Explore 4 versions of Qwen3.8. Compare model sizes, packages, hardware requirements, and available setups.

4 versionsCompare sizes & formats
LOCALRENTED GPU
Compare versions →