alt.freeweights.qwen / MiMo-V2.6-Distill-Qwen-9B
From: XiaomiMiMo <huggingface.co/XiaomiMiMo>Newsgroups: alt.freeweights.qwenSubject:

MiMo-V2.6-Distill-Qwen-9B

Date: 2026-11-14Commit: 1f09ddcSigned: 2DC28CC7B26A283B ✓

Image text to text model with 9.4B parameters. Safetensors weights, 18.8 GB in all. Published by XiaomiMiMo under MIT.

9.4B params18.8GBMiMo-V2.6-Distill-Qwen-9Bsafetensorspermissive
FactsParams9.4BSize18.8 GBFormatssafetensorsTaskimage text to textLicenseMITFrom sourcepermissive
$ fw get XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B
# manifest sha256 744053578fd1… · 18.8 GB · 17 files
$ fw verify ./MiMo-V2.6-Distill-Qwen-9B XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B
From sourceHosted (signed)XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9BLast check: 2026-11-14 06:33 UTC

Get help: custom fine-tune or private deploy. We review your setup before we quote.

Fine-tune of Qwen3.5-9B.

Works with

Overview

Size
18.8 GB
Weights
18.8 GB (safetensors)
Parameters
9.4B
Formats
safetensors
Task
image text to text
License
MIT (permissive)
Files
17, each with a sha256
Publisher
XiaomiMiMo
Added
2026-11-14
Section
alt.freeweights.qwen
Lineage

Original release from the publisher.

Base model: Qwen/Qwen3.5-9B

Where these bytes come from
Publisher at the pinned commit→You

Sources are tried in order. A file counts only when its size and sha256 match the manifest. Sources are checked when you ask for them, not on a timer.

Sources
BadgeHostLast checkResult
From sourcehuggingface.co2026-11-14 06:33 UTCpassed

Model card

From the publisher at commit 1f09ddc. Shown as plain text with links; images open at the publisher.

MiMo-V2.6-Distill-Qwen-9B#

MiMo-V2.6-Distill-Qwen-9B is a 9B agentic model developed by Xiaomi MiMo through supervised fine-tuning of Qwen3.5-9B on MiMo-generated data. It covers coding, general-purpose agent tasks, visual coding, and cybersecurity. We release this SFT checkpoint as a starting point for open research in agentic reinforcement learning.

Evaluation#

Results for the released SFT checkpoint, as reported in the MiMo-V2.6 technical report.

DomainBenchmarkMetricQwen3.5-9BMiMo-V2.6-Distill-Qwen-9B (SFT)
CodeSWE Verifiedavg@360.061.1
CodeSWE Proavg@332.044.6
CodeMiMo Code (mini)†avg@319.551.6
CyberMiMo Cyber (mini)†avg@35.731.3
GeneralAutomationBench v1.0.6avg@15.030.3
GeneralTerminal Bench 2.1avg@127.037.1
GeneralToolathlon-Verifiedavg@125.935.2
GeneralOfficeQAavg@19.019.5
GeneralJobBenchavg@12.618.3
GeneralMiMo General (mini)†avg@128.562.2
VisualMiMo Visual Coding (mini)†avg@161.764.0

† Internal evaluation sets.

Training Data#

The weighted SFT data mixture contains 77.4B total tokens, including 27.2B loss-bearing tokens.

DomainTotal tokens (B)Token share (%)Loss-bearing tokens (B)
Code23.229.97.3
Cyber11.014.24.8
General22.028.55.7
Visual21.227.49.4
Total77.4100.027.2

Quickstart#

For text generation, use a recent SGLang build with Qwen3.5 support. The checkpoint includes its tokenizer and MiMo v2.6 chat template.

sglang serve \
  --model-path XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B \
  --reasoning-parser mimo \
  --host 0.0.0.0 \
  --port 30000

Query the endpoint with thinking explicitly enabled:

from openai import OpenAI

client = OpenAI(
    base_url="http://localhost:30000/v1",
    api_key="EMPTY",
)

response = client.chat.completions.create(
    model="XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B",
    messages=[
        {"role": "user", "content": "What is 15% of 240?"}
    ],
    max_tokens=2048,
    extra_body={"chat_template_kwargs": {"enable_thinking": True}},
)

message = response.choices[0].message
print("Thinking:", getattr(message, "reasoning_content", "") or "")
print("Answer:", message.content or "")

Citation#

@misc{mimo2026v26,
  title={MiMo-V2.6: Scaling Reinforcement Learning Towards Self-Improvement},
  author={{Xiaomi MiMo Team}},
  year={2026},
  howpublished={\url{https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Pro-RL}},
}

Use Restrictions#

You are solely responsible for your use of XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B and any outputs, actions, or consequences arising therefrom, and you agree not to use the XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B or any derivatives thereof:

  • For any unlawful, fraudulent, or malicious purpose, or in any manner that violates any applicable laws or regulations;
  • To infringe upon the intellectual property rights, privacy rights, publicity rights, or other lawful rights or interests of any third party;
  • To exploit, harm, harass, defame, unlawfully discriminate against, or otherwise adversely affect any individual or group, including minors or vulnerable persons;
  • For any military purpose or application;
  • To engage in or facilitate malicious cyber activities, including but not limited to malware, ransomware, phishing, credential theft, or unauthorized access, or any activity intended to compromise or unlawfully control computer systems, networks, or encryption systems;
  • To access, collect, process, disclose, or disseminate personal data or other protected information without appropriate authorization or lawful basis; or to access, interact with, scrape, or automate any third-party platform or service in violation of any applicable laws, policies, or authorization requirements;
  • To use the XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B in a manner that autonomously executes high-risk actions without appropriate human oversight or authorization.

This notice is an informational reminder only and does not amend the applicable model licence or impose additional licence conditions. The permissions granted under that licence remain unaffected. Nothing in this notice restricts uses permitted by applicable law, including applicable exceptions and limitations.

Usage enquiries and complaints#

mimo-legal@xiaomi.com. For information on submitting a complaint, please visit the https://mimo.xiaomi.com.

Files

17 files · 18.8 GBWeights 18.8 GB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 17 files with their sha256
FileSizesha256
.gitattributes1.57 KB34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930
README.md5.00 KB2df418b6e978a8c46ac2b9e60fb4efbddac5fb5be122f196fb8520a0ba68a59d
chat_template.jinja3.92 KB59a64ebb4df6d1489d09a91267cf3ceb106162d4a893c4f84833cfb8c897ff63
config.json2.78 KB407c46388b8fa2ae9bf69fe27d40af236d373e86a6b48f5284c86df5cd183633
generation_config.json126 Baaed5b26f1cae55c1ceb58fc483c3cd65ee8d386b61daec3d7a9df82432d9205
merges.txt3.35 MBa9d356d7bdf1ef4949e3e748e95b8e10ad9d4e2e838eddc38a0a7b6b94d1db8d
model-00001-of-00004.safetensors5.28 GBaab052180118aee34abc3029b54eaa49096aac606b97d703866b420dceb703c3
model-00002-of-00004.safetensors5.03 GB7a0486565f06d25ac4628e9dba470dc3f604353471d240d5a0bf7128f64df396
model-00003-of-00004.safetensors5.23 GB6c73207563d1879bfd6c143a028cc70be68edff56280458c71a43df4240300f4
model-00004-of-00004.safetensors3.28 GB1379a7cf8c0b8555a39ab65a47e830e0eb45e776b46045734da3afd73c09eea2
model.safetensors.index.json69.2 KB4a24d25e902169c0393a2ca58b697c03b27efc40dcddbc2b59c42e5e1e2b1d90
preprocessor_config.json443 B3a159dfec9978a186a72ba085e0ad6a050f3968d8b364218d7bd13f5c89381f2
processor_config.json1.19 KBd89ef49ce9cd37fbf510158e13c1ef063d9286411c1ec9049932dbe0487143b1
tokenizer.json20.0 MB06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
tokenizer_config.json1.17 KB792fa3f0cb88b111e54ef3134c873531008c4df471d108da17903426e308aa7b
video_preprocessor_config.json385 B7768af27c1fafa9cc9011c1dc20067e03f8915e03b63504550e11d5066986d13
vocab.json6.72 MBce99b4cb2983d118806ce0a8b777a35b093e2000a503ebde25853284c9dfa003
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
1f09ddcc1a pinned now2026-11-14 06:33 UTC17 files · 18.8 GB

Use it

$ fw get XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B
# manifest sha256 744053578fd1… · 18.8 GB · 17 files
$ fw verify ./MiMo-V2.6-Distill-Qwen-9B XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B.json --dir ./MiMo-V2.6-Distill-Qwen-9B $ python3 fw.py verify ./MiMo-V2.6-Distill-Qwen-9B ./XiaomiMiMo__MiMo-V2.6-Distill-Qwen-9B.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B --revision 1f09ddcc1a0ea45751ae0dfe2af20d533168c46f --local-dir ./MiMo-V2.6-Distill-Qwen-9B
transformersLoad the weights in Python.
import os os.environ["HF_ENDPOINT"] = "https://freeweights.allternit.com" from transformers import AutoModelForImageTextToText, AutoProcessor processor = AutoProcessor.from_pretrained("XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B", revision="1f09ddcc1a0ea45751ae0dfe2af20d533168c46f") model = AutoModelForImageTextToText.from_pretrained("XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B", revision="1f09ddcc1a0ea45751ae0dfe2af20d533168c46f", device_map="auto")
vLLMServe an OpenAI-compatible API.
$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B --revision 1f09ddcc1a0ea45751ae0dfe2af20d533168c46f

License

Name
MIT License
Id
MIT
Class
Permissive
Redistribution
yes
Listing
Hosted (signed)
Decided
Checked and recorded in the license audit. 2026-11-14
Text in
README.md
Text sha256
2df418b6e978a8c46ac2b9e60fb4efbddac5fb5be122f196fb8520a0ba68a59d
Terms gate
No extra terms beyond the license.

Read the license text

Licenses are checked against the license table. A custom license passes only after a person reads it.

Provenance

From: XiaomiMiMo <huggingface.co/XiaomiMiMo>Newsgroups: alt.freeweights.qwenSubject: MiMo-V2.6-Distill-Qwen-9BDate: 2026-11-14Commit: 1f09ddcSigned: 2DC28CC7B26A283B ✓
Upstream
XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B
Pinned commit
1f09ddcc1a0ea45751ae0dfe2af20d533168c46f
Manifest
MiMo-V2.6-Distill-Qwen-9B.json · .minisig
Manifest sha256
744053578fd1c2b33f8e7e45765a1d0e83cf0fed8235b52e0c595c3b5875c84d
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-14 06:33 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B.json $ curl -O https://freeweights.allternit.com/manifests/XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B.json.minisig $ minisign -Vm MiMo-V2.6-Distill-Qwen-9B.json -P RWQ7KGqyx4zCLXtUFOqvfv8L3g+8fpKJ1FsuxPyOYMF+4KufbUxKq1Oq $ shasum -a 256 <file> # compare with the Files tab

A manifest whose signature fails must be rejected. A file whose size or sha256 does not match must be discarded. Verify a download

Model tree

Parent

Qwen/Qwen3.5-9B · this model is a finetune of it

3 models in the catalog name this one as their parent.

Quantizations
3
Get it
Download
$ HF_ENDPOINT=https://freeweights.allternit.com hf download XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B
Open in Freeweights Studio

Pull, verify and run it in the Allternit app on Desktop, web or phone.

Signed manifest
minisign, key 2DC28CC7B26A283B. MiMo-V2.6-Distill-Qwen-9B.json. Provenance. Takedown history: none.

Variants

3 quantized or adapter builds of MiMo-V2.6-Distill-Qwen-9B. Each has its own license check and page.

From: BAAI <huggingface.co/BAAI>Subject: Aquila-VL-2B-llava-qwen
From: Perciqa <huggingface.co/Perciqa>Subject: Aurora-Code-1
From: BAAI <huggingface.co/BAAI>Subject: bge-reasoner-embed-qwen3-8b-0923
From: amazon <huggingface.co/amazon>Subject: BMOJOF-primed-HQwen3-8B-Instruct
From: nbeerbower <huggingface.co/nbeerbower>Subject: Bubba-Qwen3.6-27B-LoRA
From: bartowski <huggingface.co/bartowski>Subject: bytkim_Qwen3.8-27B-pi-GGUF