Instructions to use xunlinkx/MiMo-V2.6-Distill-Qwen-9B-Text-oQ3e with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use xunlinkx/MiMo-V2.6-Distill-Qwen-9B-Text-oQ3e with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("xunlinkx/MiMo-V2.6-Distill-Qwen-9B-Text-oQ3e")

prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True
)

text = generate(model, tokenizer, prompt=prompt, verbose=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use xunlinkx/MiMo-V2.6-Distill-Qwen-9B-Text-oQ3e with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "xunlinkx/MiMo-V2.6-Distill-Qwen-9B-Text-oQ3e"

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "xunlinkx/MiMo-V2.6-Distill-Qwen-9B-Text-oQ3e"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use xunlinkx/MiMo-V2.6-Distill-Qwen-9B-Text-oQ3e with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "xunlinkx/MiMo-V2.6-Distill-Qwen-9B-Text-oQ3e"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "xunlinkx/MiMo-V2.6-Distill-Qwen-9B-Text-oQ3e"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "xunlinkx/MiMo-V2.6-Distill-Qwen-9B-Text-oQ3e",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use xunlinkx/MiMo-V2.6-Distill-Qwen-9B-Text-oQ3e with Hermes Agent:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "xunlinkx/MiMo-V2.6-Distill-Qwen-9B-Text-oQ3e"

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default xunlinkx/MiMo-V2.6-Distill-Qwen-9B-Text-oQ3e

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use xunlinkx/MiMo-V2.6-Distill-Qwen-9B-Text-oQ3e with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "xunlinkx/MiMo-V2.6-Distill-Qwen-9B-Text-oQ3e"

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "xunlinkx/MiMo-V2.6-Distill-Qwen-9B-Text-oQ3e" \
  --custom-provider-id mlx-lm \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

MiMo-V2.6-Distill-Qwen-9B-Text-oQ3e

An Apple MLX enhanced oQ3 (oQ3e) quantization of XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B, built with oMLX using 128 calibration samples at sequence length 512, strict importance-matrix coverage, BF16 compute, and group size 64.

Modality: Pure Text-Only (LLM). Vision tower weights and multimodal processor configs have been cleanly omitted. This yields a significantly leaner memory footprint, drastically lower RAM usage, and instant loading in any standard text inference pipeline (Cursor, OpenHands, LM Studio, vanilla mlx-lm.generate).

This model is built without speculative MTP draft heads for maximum compatibility with standard mlx-lm and minimal unified memory / VRAM consumption.

Validation

Validated locally before upload on 2026-09-25:

strict model loading through the oMLX runtime
global 3-bit affine quantization metadata with group size 64
complete strict oQe importance-matrix application (no missing or mismatched entries)
tokenizer SHA-256 identity across source and output
official chat template renders an OpenAI-style function schema
deterministic generation smoke test (15% of 240 includes 36)

The machine-readable validation report is included as validation.json.

Notes

Built specifically for the oMLX runtime. Point to upstream base model cards for original training details.
Tool use depends on applying the included chat template and supplying tool schemas in the request.
Quantization can change behavior. Evaluate on your own workload before production use.

License

MIT, following the upstream model. See the upstream repositories for their respective notices and attribution.

Downloads last month: 195

Safetensors

Model size

9B params

Tensor type

U32

BF16

MLX

Hardware compatibility

3-bit

Model tree for xunlinkx/MiMo-V2.6-Distill-Qwen-9B-Text-oQ3e

Base model

Qwen/Qwen3.5-9B-Base

Finetuned

Qwen/Qwen3.5-9B

Finetuned

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

Quantized

(53)

this model