LocalClaw/LLM/MiMo-V2.6-Flash-RL
Open-weight MoE

MiMo-V2.6-Flash-RL

Use case: Coding assistant. Check the memory fit and choose a setup path below.

160 GB catalogue minimum160 GB RAMQ2_K GGUFCoding assistant
Choose an app

This is an advanced workstation/server GGUF path. Unsupported apps are clearly marked.

Compare models
LM StudioNot available for this model
Open in UnslothLaunches Unsloth Desktop on this model's download page
OllamaNot available for this model
Open on Hugging FaceFiles, licence and available downloadsOpen llama.cpp setupAdvanced option: opens GGUF files and patch notesUse with LocalClawOptional workspace after the model is installed

Desktop app links require the app to be installed. If nothing opens, LocalClaw will show app-download and model-file fallbacks.

Parameters
309B (15B active, MoE)
Minimum RAM
160 GB
Model size
126.4 GB
Quantization
Q2_K GGUF

About MiMo-V2.6-Flash-RL

Catalogue summary: Official Xiaomi MiMo MIT-licensed sparse MoE with 309B total / 15B active parameters, native text-image-video-audio support, 1M-token context and ggml-org GGUF artifacts for llama.cpp-class workstation experiments.

MiMo-V2.6-Flash-RL has a catalogue minimum of 160 GB RAM with Q2_K GGUF. Actual memory use and speed vary by context length, runtime, backend and system headroom.

Treat mimo-v2.6-flash-rl as an advanced workstation/server-grade catalogue target with verified GGUF artefacts. Open the GGUF files and follow the upstream runtime notes; LocalClaw does not claim a one-click LM Studio install.

Model sourcePublic GGUF repository (verified 2026-11-06): ggml-org/MiMo-V2.6-Flash-RL-GGUFUpstream releasePaper or model cardLicence text
chatcodereasoningvisionagenticbeastlong-contextmultimodal

Deployment path

01
Check RAM fitServer-grade target. Plan for 160 GB class multi-GPU memory.
02
Load the modelOpen the verified GGUF files for mimo-v2.6-flash-rl and follow the upstream runtime or patch notes first.
03
Try your workloadStart with a short prompt, check memory use and adjust context length before running longer tasks.

Catalogue record

  • Family: mimo
  • Parameters: 309B (15B active, MoE)
  • Recommended quantization: Q2_K GGUF
  • Catalogue minimum RAM: 160 GB
  • Catalogue model size: 126.4 GB
  • Tags: chat, code, reasoning, vision, agentic, beast, long-context, multimodal, moe

Practical limits

  • Catalogue RAM is a minimum estimate, not a guarantee for every context length or runtime.
  • Speed and memory use vary by quantization, backend, context length and system headroom.
  • Verify architecture, licence and usage restrictions in the linked upstream material before deployment.

Reading the scores

LocalClaw /10 is an editorial catalogue rating. Community /5 comes from member reviews. Your machine fit is a separate memory and runtime assessment.

Capability profile

Repository catalogue ratings used by LocalClaw's editorial rubric. They are not a standardized third-party benchmark.

speed
4
quality
10
coding
10
reasoning
10

Technical notes

Developer
Xiaomi MiMo
License
MIT
Context window
1,000,000 tokens
Architecture
Sparse Mixture-of-Experts omnimodal language model with 309B total parameters, about 15B activated parameters per token, 256 routed experts, eight selected experts, 48 transformer layers and 1,048,576-token context.

This model fits these next steps

Hardware fit is based on LocalClaw's RAM tier, model size and quantization metadata. Always leave memory headroom for your OS and runtime.

Very large memoryMac Studio Ultra classCheck model size firstNVIDIA GB10 / server optionsMore practical alternativesCompare smaller models

Related catalogue entries

Linked mechanically by family, shared tags and nearby RAM tier; this is not a quality ranking.

GLM-5.3-Flash 320B (18B active, MoE)Qwen3.8 Flash Next 125B + 51B n-gram (6B active)DeepSeek V4 Flash Vision Exp 284B (13B active, multimodal MoE)DeepSeek V4.1 Flash 552B MoE (8B/16B active)Ling Flash Base 2.0 106B (6.1B active, MoE)Bonsai 2 27B 27.36B (ternary)Bonsai 27B 27.3B (ternary / 1-bit)K2-Horizon-MoVA-36B-A4B 36B (4B active, MoE)

Where to go next