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
- 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 result
Across MiMo V2.6 sizes
| Benchmark (publisher settings) | Flash 309B | Pro 1.02T |
|---|---|---|
| DeepSWE v1.1 | 67.9 | 71.9 |
| ProgramBench | 26.0 | 26.5 |
| MiMo Code Bench | 61.2 | 63.2 |
| AutomationBench v1.0.6 | 52.3 | 53.1 |
| Toolathlon-Verified | 73.6 | 76.9 |
| Agents’ Last Exam | 27.6 | 31.6 |
| Terminal Bench 4.0 | 28.8 | 34.9 |
| Terminal Bench 2.1 | 87.6 | 89.9 |
| OSWorld-Verified | 80.8 | 82.0 |
| JobBench | 61.2 | 62.0 |
| CyberGym | 95.1 | 94.0 |
| MiMo Cyber Bench | 77.2 | 80.2 |
| ExploitGym | 6.0 | 17.8 |
| ExploitBench | 25.3 | 47.9 |
| SEC Bench Pro | 47.5 | 66.3 |
| MiMo VisualCoding | 71.5 | 72.3 |
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
| 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 GB | Larger than its memory | No file on the site's quant ladder fits the fast memory at 8,192 tokens | No 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 GB | Larger than its memory | No file on the site's quant ladder fits the fast memory at 8,192 tokens | No 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 GB | Larger than its memory | No file on the site's quant ladder fits the fast memory at 8,192 tokens | No 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 GB | Larger than its memory | No file on the site's quant ladder fits the fast memory at 8,192 tokens | No 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 GB | Larger than its memory | No file on the site's quant ladder fits the fast memory at 8,192 tokens | No 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 GB | Larger than its memory | No file on the site's quant ladder fits the fast memory at 8,192 tokens | No 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 GB | Fast memory holds it | No file on the site's quant ladder fits the fast memory at 8,192 tokens | No 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 GB | Larger than its memory | No file on the site's quant ladder fits the fast memory at 8,192 tokens | No 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 GB | Larger than its memory | No file on the site's quant ladder fits the fast memory at 8,192 tokens | No 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 GB | Larger than its memory | No file on the site's quant ladder fits the fast memory at 8,192 tokens | No 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 GB | Larger than its memory | No file on the site's quant ladder fits the fast memory at 8,192 tokens | No 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 GB | Larger than its memory | No file on the site's quant ladder fits the fast memory at 8,192 tokens | No 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 GB | Fast memory holds it | No file on the site's quant ladder fits the fast memory at 8,192 tokens | No 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.
Compare MiMo V2.6 Flash using its publisher card. No overall score appears in the LiveBench 2026-06-25 snapshot.
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_Klms 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 versions
- 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 versions
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
- Check the exact checkpoint and license linked here.
- Confirm a compatible runtime and precision or quantization for your platform.
- 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 field
- Revision checked
- 5711b268169967567844e1e560e8a3966da959b1
- Architecture
- MiMoV2ForCausalLM
- Library
- transformers
- Hub task tag
- text-generation
- Distributions in this group
- mlx-community/MiMo-V2.6-Flash-RL-mxfp4-q8
- 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.
- Publisher checkpoint and model card
- Weight license and use terms
- Quality benchmark source · LiveBench 2026-06-25 overall
Catalog reviewed: 2026-09-30. Benchmark release: 2026-06-25; snapshot collected: 2026-10-18.








