What are the hardware requirements for MiMo V2.6 Flash RL?

MiMo V2.6 Flash RL requires approximately 1.2 GB of VRAM and supports a context window of 1024K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed MiMo V2.6 Flash RL and how large is it?

MiMo V2.6 Flash RL is developed by XiaomiMiMo, a model with 310.8b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate MiMo V2.6 Flash RL?

MiMo V2.6 Flash RL is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

MiMo V2.6 Flash RL by XiaomiMiMo — VRAM 1.2GB, 1024K context

Name: MiMo V2.6 Flash RL
Author: XiaomiMiMo

MiMo V2.6 Flash RL is an open-source language model by XiaomiMiMo. Features: 310.8b LLM, VRAM: 1.2GB, Context: 1024K, License: mit, LLM Explorer Score: 0.57.

8-bit Agent Audio Conversational Custom code En Eval-results Fp8 Long-context Mimo v2 Multimodal Region:us Safetensors Video-understanding Vision Vision-language Zh

Model Card on HF 🤗: https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL

MiMo V2.6 Flash RL Parameters and Internals

LLM Name	MiMo V2.6 Flash RL
Repository 🤗	https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL
Model Size	310.8b
Required VRAM	1.2 GB
Updated	2026-09-24
Maintainer	XiaomiMiMo
Model Type	mimo_v2
Model Files	1.2 GB 13.4 GB 2.5 GB 2.5 GB 2.5 GB 2.5 GB 2.5 GB 2.5 GB 2.5 GB 2.5 GB 2.5 GB 2.5 GB 2.5 GB 2.5 GB 2.5 GB 2.5 GB 2.5 GB 2.5 GB 2.5 GB 2.5 GB 2.5 GB 2.5 GB 2.5 GB 2.5 GB 2.5 GB 2.5 GB 2.5 GB 2.5 GB 2.5 GB 2.5 GB 2.5 GB 2.5 GB 2.5 GB 2.5 GB 2.5 GB 2.5 GB 2.5 GB 2.5 GB
Supported Languages	en zh
Model Architecture	MiMoV2ForCausalLM
License	mit
Context Length	1048576
Model Max Length	1048576
Transformers Version	5.3.0
Vocabulary Size	152576

Rank the MiMo V2.6 Flash RL capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Quantized Models of the MiMo V2.6 Flash RL

Model	Likes	Downloads	VRAM
...iMo V2.6 Flash RL MLX 4bit MTP	9	1688	164 GB
MiMo V2.6 Flash RL Mxfp4 Q8	1	687	168 GB

Best Alternatives to MiMo V2.6 Flash RL

Best Alternatives	Context / RAM	Downloads	Likes
MiMo V2.5	1024K / 1.2 GB	339077	377