Instructions to use wesjos/Mimo-Qwen3.5-9B-Cold-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use wesjos/Mimo-Qwen3.5-9B-Cold-GGUF with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="wesjos/Mimo-Qwen3.5-9B-Cold-GGUF")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("wesjos/Mimo-Qwen3.5-9B-Cold-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use wesjos/Mimo-Qwen3.5-9B-Cold-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf wesjos/Mimo-Qwen3.5-9B-Cold-GGUF:Q8_0
# Run inference directly in the terminal:
llama cli -hf wesjos/Mimo-Qwen3.5-9B-Cold-GGUF:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf wesjos/Mimo-Qwen3.5-9B-Cold-GGUF:Q8_0
# Run inference directly in the terminal:
llama cli -hf wesjos/Mimo-Qwen3.5-9B-Cold-GGUF:Q8_0

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf wesjos/Mimo-Qwen3.5-9B-Cold-GGUF:Q8_0
# Run inference directly in the terminal:
./build/bin/llama cli -hf wesjos/Mimo-Qwen3.5-9B-Cold-GGUF:Q8_0

Use Docker

docker model run hf.co/wesjos/Mimo-Qwen3.5-9B-Cold-GGUF:Q8_0

Llama new
LM Studio
Jan

vLLM

How to use wesjos/Mimo-Qwen3.5-9B-Cold-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "wesjos/Mimo-Qwen3.5-9B-Cold-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "wesjos/Mimo-Qwen3.5-9B-Cold-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/wesjos/Mimo-Qwen3.5-9B-Cold-GGUF:Q8_0

SGLang

How to use wesjos/Mimo-Qwen3.5-9B-Cold-GGUF with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "wesjos/Mimo-Qwen3.5-9B-Cold-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "wesjos/Mimo-Qwen3.5-9B-Cold-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "wesjos/Mimo-Qwen3.5-9B-Cold-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "wesjos/Mimo-Qwen3.5-9B-Cold-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use wesjos/Mimo-Qwen3.5-9B-Cold-GGUF with Ollama:
```
ollama run hf.co/wesjos/Mimo-Qwen3.5-9B-Cold-GGUF:Q8_0
```
Unsloth Desktop

How to use wesjos/Mimo-Qwen3.5-9B-Cold-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf wesjos/Mimo-Qwen3.5-9B-Cold-GGUF:Q8_0

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "wesjos/Mimo-Qwen3.5-9B-Cold-GGUF:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use wesjos/Mimo-Qwen3.5-9B-Cold-GGUF with Docker Model Runner:
```
docker model run hf.co/wesjos/Mimo-Qwen3.5-9B-Cold-GGUF:Q8_0
```

Lemonade

How to use wesjos/Mimo-Qwen3.5-9B-Cold-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull wesjos/Mimo-Qwen3.5-9B-Cold-GGUF:Q8_0

Run and chat with the model

lemonade run user.Mimo-Qwen3.5-9B-Cold-GGUF-Q8_0

List all available models

lemonade list

Hermes Agent

How to use wesjos/Mimo-Qwen3.5-9B-Cold-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf wesjos/Mimo-Qwen3.5-9B-Cold-GGUF:Q8_0

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 wesjos/Mimo-Qwen3.5-9B-Cold-GGUF:Q8_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use wesjos/Mimo-Qwen3.5-9B-Cold-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf wesjos/Mimo-Qwen3.5-9B-Cold-GGUF:Q8_0

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 "wesjos/Mimo-Qwen3.5-9B-Cold-GGUF:Q8_0" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

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

MiMo-9B-Cold (LIMA DPO)

A cold-style preference-aligned model built on MiMo-V2.6-Distill-Qwen-9B: DPO applied directly to the base model (no SFT), using 1,027 modified LIMA-style preference pairs to make responses concise, decisive, and direct — while preserving intelligence and general knowledge.

📋 Model Overview

Attribute	Value
Model Name	wesjos/Mimo-Qwen3.5-9B-Cold
Base	MiMo-V2.6-Distill-Qwen-9B (Qwen3.5-architecture distill, 9.4B params)
Method	DPO (Direct Preference Optimization), skipping SFT
Training Data	`lima_dpo_clean.jsonl` — 1,027 LIMA-style preference pairs
Training Framework	Unsloth + TRL DPOTrainer (QLoRA 4bit)
Release Formats	HF merged_16bit (18 GB) · LoRA adapter · GGUF Q8_0 (8.87 GB)
Context Length	262,144 (native)
Languages	English / Chinese

🚀 Usage

Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained(
    "<repo>/merged_16bit", torch_dtype="bfloat16", device_map="auto"
)
tok = AutoTokenizer.from_pretrained("<repo>/merged_16bit")

messages = [{"role": "user", "content": "Introduce yourself in two sentences."}]
inputs = tok.apply_chat_template(
    messages, tokenize=True, add_generation_prompt=True,
    enable_thinking=False, return_tensors="pt", return_dict=True,
).to("cuda")
out = model.generate(**inputs, max_new_tokens=300, temperature=0.6, top_p=0.9)
print(tok.decode(out[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))

llama.cpp (GGUF Q8_0)

llama-server -m mimo-9b-cold-Q8_0.gguf \
  --ctx-size 8192 -ngl 99 -ctk q8_0 -ctv q8_0 -fa on \
  --jinja --alias mimo-9b-cold --port 18080

Recommended Parameters

temperature: 0.6, top_p: 0.9, top_k: 20
Anti-repetition: repeat_penalty 1.05, DRY multiplier 0.8
Thinking mode: template supports enable_thinking toggle

⚠️ Limitations & Notes

Small training scale: only 1 epoch × 1,027 pairs — lightweight style alignment; do not expect capability gains, only style transfer
Slightly higher tool hallucination rate: for function calling, add parameter schema validation at the application layer
Knowledge cutoff: inherited from the base model (Qwen3.5 family); training data contains no new knowledge
Safety alignment: retains the base model's full safety values (illegal requests are refused with lawful alternatives)
BBH sampling variance: at limit 200 each subset has only ~4 questions; the -2.78pp drop is not statistically significant