Skip to content
Local AI Wizard
Your machine
Theme

MiMo V2.6 Flash

Xiaomi · XiaomiMiMo/MiMo-V2.6-Flash-RL

Text & chatVisionVideoAudio

Runs well from 512 GB · Weights license: MIT

LMArena · text1,448 ± 6Rank 81 · release 2026-10-22 · its own scale
Memory needed~232 GBQ4 weights + working room, before the machine's reserve
Parameters309 Bmanufacturer specification · 15B active
Context1,048,576 tokensPublished for this model

Quality

LMArena · text · rating
1,448 ± 6Confidence interval 1,442–1,454 · 13,730 votes · rank 81 of the releaseLMArena 2026-10-22 · CC BY 4.0

No result in LiveBench 2026-06-25 Not in LiveBench 2026-06-25

Reported by the publisher

16 results · Xiaomi's model card · read 2026-10-25
DeepSWE v1.1
67.9Code Agent
ProgramBench
26.0Code Agent
MiMo Code Bench
61.2Code Agent
AutomationBench v1.0.6
52.3General Agent
Toolathlon-Verified
73.6General Agent
Agents’ Last Exam
27.6General Agent
Terminal Bench 4.0
28.8General Agent
Terminal Bench 2.1
87.6General Agent
Every reported result16
OSWorld-Verified
80.8General Agent
JobBench
61.2General Agent
CyberGym
95.1Cybersecurity
MiMo Cyber Bench
77.2Cybersecurity
ExploitGym
6.0Cybersecurity
ExploitBench
25.3Cybersecurity
SEC Bench Pro
47.5Cybersecurity
MiMo VisualCoding
71.5Visual Agent
Across MiMo V2.6 sizes16 shared results · same publisher and settings
MiMo V2.6: results the publisher reports for each size under the same settings
Benchmark (publisher settings)Flash 309BPro 1.02T
DeepSWE v1.1 · Code Agent67.971.9
ProgramBench · Code Agent26.026.5
MiMo Code Bench · Code Agent61.263.2
AutomationBench v1.0.6 · General Agent52.353.1
Toolathlon-Verified · General Agent73.676.9
Agents’ Last Exam · General Agent27.631.6
Terminal Bench 4.0 · General Agent28.834.9
Terminal Bench 2.1 · General Agent87.689.9
OSWorld-Verified · General Agent80.882.0
JobBench · General Agent61.262.0
CyberGym · Cybersecurity95.194.0
MiMo Cyber Bench · Cybersecurity77.280.2
ExploitGym · Cybersecurity6.017.8
ExploitBench · Cybersecurity25.347.9
SEC Bench Pro · Cybersecurity47.566.3
MiMo VisualCoding · Visual Agent71.572.3

Values as printed on the card, with the publisher's own settings (card section: 3. Evaluation Results); column “MiMo-V2.6 Flash”. Not comparable across publishers and not used in any ranking. Model card

Runs on

Fast memory holds it 1

The planning estimate fits the memory the model can use quickly: graphics card VRAM, or unified memory within the macOS GPU share.

Within memory, outside the fast part 1

Within the machine's memory, outside its fast part: on a graphics card the layers that do not fit run on the CPU from PC RAM (the listed RAM, or 32 GB assumed); on a Mac, above the macOS default GPU share. Not a speed figure.

One memory tier short 9

The same machines with the next memory size up would hold it in fast memory.

Show all 9

MiMo V2.6 Flash is a text model from Xiaomi with 309B parameters, 15B of them active per token (mixture of experts). It was released on September 22, 2026 and reads up to 1,048,576 tokens of context. Its Q4 weights plus working room come to about 232 GB before the machine's reserve; the smallest reference machine whose fast memory holds that is Mac Studio · M5 Ultra · 36-core CPU / 80-core GPU · 512 GB unified (~240 GB with its reserve). We collected 2 downloadable GGUF files from one publisher; the most downloaded GGUF source is ggml-org's (19.1K downloads on the Hub). It has no result in LiveBench 2026-06-25. Its LMArena text rating is 1,448 ± 6 (release 2026-10-22), a separate human-preference scale.

Hardware profiles grouped by the Q4 planning estimate on each machine (dedicated GPUs reserve 2 GB; unified and system memory 25%, 2 to 8 GB): the fast memory holds it, it is within memory but outside the fast part (layers offloaded to PC RAM, or above the macOS GPU share), or the machine is one memory tier short. Each card opens its hardware profile. Not a measured fit or speed.

On the reference machines

MiMo V2.6 Flash on the reference machines
Where Q4 sits
Mac mini M2 · 8 GB unifiedLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column~234 GBLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column
Mac mini M4 · 16 GB unifiedLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column~236 GBLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column
Mac mini M4 · 24 GB unifiedLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column~238 GBLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column
Mac mini M4 · 32 GB unifiedLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column~240 GBLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column
Mac mini M5 Pro · 64 GB unifiedLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column~240 GBLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column
Mac Studio M5 Max · 128 GB unifiedLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column~240 GBLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column
Mac Studio · M5 Ultra · 36-core CPU / 80-core GPU · 512 GB unifiedFast memory holds itNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column~240 GBFast memory holds itNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column
RTX 4060 · 8 GB VRAMLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column~234 GBLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column
RTX 3060 · 12 GB VRAMLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column~234 GBLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column
RTX 5080 · 16 GB VRAMLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column~234 GBLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column
RTX 4090 · 24 GB VRAMLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column~234 GBLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column
RTX 5090 · 32 GB VRAMLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column~234 GBLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column
DGX H100 · 8 × 80 GBFast memory holds itNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column~248 GBFast memory holds itNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column

The file column uses the site's quant ladder (Q8_0 to Q3_K_M, MLX 8 to 4-bit on a Mac): the largest collected file whose size × 1.2 plus the context cache and the machine's reserve fits the fast memory. Planning estimates, not measured runs.

Plan another quantization or context

Consider it for

Compare MiMo V2.6 Flash using its publisher card. No overall score appears in the LiveBench 2026-06-25 snapshot.

Check first

The Q4 weights plus working room come to about 232 GB from 309B stated parameters, before the machine's reserve (Runs on adds it per machine). It is not a measured minimum; context, batch size, runtime and quantization change actual memory use.

Versions to download

Files you can download for this checkpoint. The section opens on the most downloaded collected GGUF source, ggml-org (19.1K Hub downloads), at Q2_K. Sizes are the Hub's published bytes. What is quantization?

GGUF · the only format collected

ggml-org · 19.1K downloads

ggml-org/MiMo-V2.6-Flash-RL-GGUF · MiMo-V2.6-Flash-RL-Q2_K-00001-of-00002.gguf · 126.4 GB

Run this file

llama-server -hf ggml-org/MiMo-V2.6-Flash-RL-GGUF:Q2_K
lms get https://huggingface.co/ggml-org/MiMo-V2.6-Flash-RL-GGUF
  • Ollama: Ollama's documented hf.co form covers single-file GGUFs; this file has 2 parts
  • mlx-lm: mlx-lm runs MLX repositories; pick the MLX version on a Mac

Quality scores on this page belong to the original checkpoint; these files are not scored or ranked. File sizes read 2026-10-23 · download counts read 2026-10-17 · commands: Hugging Face Hub docs: Use Ollama with any GGUF model · llama.cpp server README (-hf <user>/<model>[:quant]) · LM Studio docs: lms get with a Hugging Face URL · mlx-lm README (mlx_lm.generate --model)

Fine-tunes, adapters and other versions5 fine-tunes
Quantized versions
38
Fine-tunes
5
Adapters · merges
2 · 0

Browse them on the Hugging Face model tree · read 2026-10-23

Uncensored and abliterated versions5

Some community uploads remove the model's safety refusals. Quality may drop, the original publisher does not support them, claims about them are the uploader's, and the original license still applies. This site never recommends or ranks them.

5 derivative repositories have “uncensored” or “abliterated” in their name (read 2026-10-23).

Measured speed

No published measurement for this checkpoint

Tokens per second are shown only when a source publishes them with hardware, build and setup. They are never estimated.

How to run

The memory needed above is the Q4 load before a machine's reserve. Formula: parameters × 0.625 bytes, plus 20% working allowance; each machine then adds its system reserve: 25% of unified or system memory, 2 to 8 GB, or 2 GB per GPU on dedicated cards. This is neither measured VRAM nor checkpoint download size.

Q4 planning estimate only. Check checkpoint format, runtime support, KV cache, context, batch size and offload before choosing hardware.

Evidence level: Generic estimate only; no execution reproduced by this site.

Publisher sampling defaults
temperature 1 · top_p 0.95generation_config.json · read 2026-10-23source
Chat template markers
tool calls · thinkingmarkers found in the template, not a test of the feature · read 2026-10-23source
Before downloading
  1. Check the exact checkpoint and license linked here.
  2. Confirm a compatible runtime and precision or quantization for your platform.
  3. Allow for context, batch size and any extra media components beyond the weights.

Technical details

What the source and the catalog store for this checkpoint. Missing fields are left out, never zero.

Checkpoint / version
XiaomiMiMo/MiMo-V2.6-Flash-RL
Task and modality
language and reasoning · text + image + video + audio
Count and basis
309B · manufacturer specification · 15B active
Context
1,048,576 tokens published for this model
Architecture
MoE
Released
Xiaomi MiMo-V2.6 Series: 3 New Models Officially Released (Xiaomi MiMo docs, update time September 22, 2026) · read 2026-10-10source
Runtime and precision
No local execution verified.
Languages
en, zhModel card metadata · read 2026-10-25source
Commercial use
Allowed MIT license text (SPDX) · read 2026-10-18license text
Every stored field12 fields
Revision checked
5711b268169967567844e1e560e8a3966da959b1
Architecture
MiMoV2ForCausalLM
Library
transformers
Hub task tag
text-generation
Formats
safetensors
Access
Open download
Publisher kind
Official
Repository created
2026-09-21creation is not the model's release
Repository updated
2026-09-22a commit is not a release date
Hub downloads (30 days) · likes
89,572 · 582this repository only · read 2026-10-25
Catalog state
Hub config or weights found; no inventory benchmark link

Sources

Identity and published specifications come from the checkpoint page. Benchmark scores belong to the named release and do not measure speed on your computer.

Catalog reviewed: 2026-09-30. Benchmark release: 2026-06-25; snapshot collected: 2026-10-18.