Marketplace · Text & chat

mimo-v2.6:9b

Call mimo-v2.6:9b through one OpenAI-compatible API. It's served by 1 host on the Inpherio grid, each at a price it sets — your request goes to the cheapest healthy one, and fails over to the next if it's down.

From
£0.06
per 1M output tokens
£1 buys about 17 million tokens (≈ 13 million words)
Hosts
1
Loaded now
0

At a glance.

vision tools reasoning

  • Type: Text & chat
  • Hosts serving it now: 1 (0 with it loaded in memory)
  • Engines: ollama
  • Context window: up to 262,144 tokens
  • Rentable: a whole host from £0.60 an hour (rentals)
python · openai sdk
from openai import OpenAI
client = OpenAI(base_url="https://inpherio.co.uk/v1",
                api_key=INPHERIO_API_KEY)
reply = client.chat.completions.create(
    model="mimo-v2.6:9b",
    messages=[{"role": "user", "content": "Hello"}],
)

mimo-v2.6:9b in detail.

MiMo-V2.6-Distill-Qwen-9B is Xiaomi MiMo’s 9B model for code and agent workflows

Published by
XiaomiMiMo
Parameters
9.4B
Download size
6.6 GB (as packaged for Ollama)
Quantisation
Q4_K_M
Format
gguf
Architecture
qwen3_5
Licence
MIT
Based on
Qwen/Qwen3.5-9B
Task
image text to text
Library
transformers
First published
21 Sep 2026
Last updated
28 Oct 2026
Downloads (30 days)
22,363 on Hugging Face
Likes
704

qwen3_5 image-text-to-text mimo_v2 agentic distillation supervised-fine-tuning code tool-use

The model card

Published by the model's authors on Hugging Face — shown as they wrote it, unedited by Inpherio.

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.

Read the rest of the model card

Usage enquiries and complaints

[email protected]. For information on submitting a complaint, please visit the https://mimo.xiaomi.com.

Sources: XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B on Hugging Face · mimo-v2.6:9b on Ollama. Collected from public sources on 14 Nov 2026; the host serving it may run a different build or quantisation — the marketplace shows each host's own measurements.

Who's serving it.

Every host benchmarked this model on its own hardware before serving it. Prices are set by each host; health is scored by the platform from what it observes.

Hosts serving mimo-v2.6:9b right now
HostTierPriceMeasured speedHealthStateRent
GTX 1080 Ti (11G)L1£0.03 in · £0.06 out4 tok/s · 19091 ms first token78loads on request£0.60/h

Live data, refreshed on every visit. How billing works.

Room on the grid for your machine.

Right now one machine serves mimo-v2.6:9b. If it drops, so does every request for it — a second host is what turns it into failover, and the grid needs that more than another copy. The router weighs price, measured speed, health and whether the model is already loaded — so a host with a sharper price or quicker hardware wins the next call.

Hosts now
1
0 loaded in memory
Price to beat
£0.06
per 1M output tokens
Fastest measured
4 tok/s

Set your own price — you keep 85% of what it earns, and new hosts start with 12 months fee-free (up to £250 of earnings). A payout fee of £2 + 1% per payout to a UK bank account, £2 + 2% to any other country applies when you're paid. Install the connector, load mimo-v2.6:9b, and the platform benchmarks it on your hardware before your first request.