whatmodel.sh / MiMo-V2.6-Distill-Qwen-9B

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

+ contribute

MiMo-V2.6-Distill-Qwen-9B is an open-weights language model from Xiaomi, released September 2026. Its published size is 9.41B parameters. Licence: mit.

Catalogue identity notes

Xiaomi SFT checkpoint: card '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' (repo created 2026-09-21, sha 2367e86, licence mit, base_model Qwen/Qwen3.5-9B). The SFT checkpoint is the released one; the report's 'RL' column in Table 6 is a set of unreleased domain-specific GRPO checkpoints and is not this model. Its card rows are alone in their run unless the owner accepts the Qwen3.5-9B comparator cells (held_for_owner).

Model information sources

Release date ↗ · Weights licence ↗

Safetensors metadata of XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B @2367e86: 9,409,813,744 parameters (includes the inherited Qwen3.5-9B vision encoder). Card: 'a 9B agentic model'.

65.3±2.2#140 of 719 LLMsfrom 5 benchmark results across 1 source

$ how it compares

The LLMs ranked either side of MiMo-V2.6-Distill-Qwen-9B, out of 828 with a score, then more from Xiaomi.

#	model	score	where	RAM	released
159	Claude 3.7 Sonnet Anthropic	65±1	comparison only		2025-02
160	Claude Sonnet 4 Anthropic	65±1	comparison only		2025-05
161	MiMo-V2.6-Distill-Qwen-9B Xiaomi	65±2	local	~7.8GB	2026-09
162	K-EXAONE (236B-A23B) LG AI Research	65±1	local	~152GB	2025-12
163	DeepSeek R1 0528 DeepSeek	65±1	api $0.91/M +local	~110GB	2025-05
	more from Xiaomi
15	MiMo-V2.6-Pro Xiaomi	79±1	api $0.54/M +local	~443GB	2026-09
27	MiMo-V2.6-Flash (309B-A15B) Xiaomi	77±1	api $0.17/M +local	~136GB	2026-09
91	MiMo-V2-Pro Xiaomi	70±1	comparison only		2026-03

see all LLMs · find the ones that fit your machine

$ what it's good at

agent tasks▁▁▃▆█▆▅▅▅▄▃▁ #119 of 300 · 88% of its score · 4 tests

Beats o3-pro, o3, GPT-5 mini here, though they rank higher overall. Trails SmolLM3 3B, Jamba 1.5 Large, Nova 2 Pro (Preview) here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
SWE-bench Pro (split unspecified) lab	44.6% ✎	▃·▁▁▁▂▂▃█▇▃▁ beats 23/55	very hard · avg 9.6%	▇▇▇▇▇▇▇▇▇▇▇▇ 29%	sharp · at its level · small run
SWE-bench Verified lab	61.1% ✎	▁▁▁▁▁▁▂▄█▆▁▁ beats 58/131	hard · avg 23%	▇▇▇▇▇▇▇▇▇▇ 26%	sharp · at its level · small run
Terminal-Bench 2.1 lab	37.1% ✎	▁·▁·▁▁▄▃▄█▃▇ beats 13/56	very hard · avg 11%	▇▇▇▇▇▇▇▇▇▇ 25%	at its level · small run
Toolathlon-Verified lab	35.2% ✎	▂·▃▂▅▃···▂██ beats 1/18	hard · avg 24%	▇▇▇ 8.1%	blunt · at its level · small run

coding▁▁▁▃▆██▇▆▄▃▁ #121 of 458 * · 55% of its score · 2 tests

Beats Qwen3.5 Plus, Gemini 2.5 Pro, Kimi K2 Thinking here, though they rank higher overall. Trails Llama 3.1 Nemotron Ultra 253B v1, Gemma 4 26B-A4B, Claude Haiku 4.5 here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
SWE-bench Pro (split unspecified) lab	44.6% ✎	▃·▁▁▁▂▂▃█▇▃▁ beats 23/55	very hard · avg 9.6%	▇▇▇▇▇▇▇▇▇▇▇▇ 29%	sharp · at its level · small run
SWE-bench Verified lab	61.1% ✎	▁▁▁▁▁▁▂▄█▆▁▁ beats 58/131	hard · avg 23%	▇▇▇▇▇▇▇▇▇▇ 26%	sharp · at its level · small run

other tests1 not in a task · 9.3% of its score

test	result	vs the others in its run	difficulty	counts	why
AutomationBench v1.0.6 lab	30.3% ✎	▃····▃·▃▃··█ beats 3/6	very hard · avg 5.5%	▇▇▇▇ 9.3%	noisy · small run

$ where to run it

llama.cpp · recommended

version

Install llama.cpp · Homebrew and winget installs name the commands llama-cli and llama-server instead.
macOS / Linux
curl -LsSf https://llama.app/install.sh | sh
Windows
irm https://llama.app/install.ps1 | iex
other ways to install ↗
Run MiMo-V2.6-Distill-Qwen-9B · needs ~6.76 GB · from huggingface.co/bartowski
chat in the terminal
llama cli -hf bartowski/MiMo-V2.6-Distill-Qwen-9B-GGUF:Q4_K_M
Or start a local server and open the address it prints (http://localhost:9931)
llama serve -hf bartowski/MiMo-V2.6-Distill-Qwen-9B-GGUF:Q4_K_M

LM Studio

version

Install LM Studio · Open the app once before using the lms command.
download it (macOS / Windows / Linux) ↗
Run MiMo-V2.6-Distill-Qwen-9B · needs ~6.76 GB · from huggingface.co/bartowski
open in LM Studio ↗
Or download it in the terminal
lms get https://huggingface.co/bartowski/MiMo-V2.6-Distill-Qwen-9B-GGUF@Q4_K_M -y
Then run lms ls to see its name, and lms chat followed by that name

Ollama

version

Install Ollama
download it (macOS / Windows) ↗
Linux
curl -fsSL https://ollama.com/install.sh | sh
Run MiMo-V2.6-Distill-Qwen-9B · needs ~6.76 GB · from huggingface.co/bartowski
chat in the terminal
ollama run hf.co/bartowski/MiMo-V2.6-Distill-Qwen-9B-GGUF:Q4_K_M

MLX (Mac)

Install MLX (Mac) · Apple silicon Macs only, text only.
with uv
uv tool install mlx-lm
or
pip install mlx-lm
Run MiMo-V2.6-Distill-Qwen-9B · needs ~6 GB, Mac only · from huggingface.co/agnosticeng
chat in the terminal
mlx_lm.chat --model agnosticeng/MiMo-V2.6-Distill-Qwen-9B-4bit
Or start an OpenAI-compatible server at http://localhost:8080/v1
mlx_lm.server --model agnosticeng/MiMo-V2.6-Distill-Qwen-9B-4bit

Weights and documentation: huggingface.co/XiaomiMiMo ↗

$ how the score was worked out · XiaomiMiMo/MiMo-V2.6-Distill-… 98%

Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works

source	results	share of the score	licence
XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B model card · lab-reported	5	▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 98%	MIT
prior · pull toward the middle		▇ 2%
weighted average		= 65.3

$ improve this page

Update model information Add a place to run it Add a test result Propose a benchmark Correct a benchmark score Edit data on GitHub

Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.

data updated 2026-10-11 02:20 UTC · sources and licences · json