Instructions to use Johnny5b/MiMo-9B-CORTEX-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Johnny5b/MiMo-9B-CORTEX-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 Johnny5b/MiMo-9B-CORTEX-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Johnny5b/MiMo-9B-CORTEX-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Johnny5b/MiMo-9B-CORTEX-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Johnny5b/MiMo-9B-CORTEX-GGUF:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf Johnny5b/MiMo-9B-CORTEX-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Johnny5b/MiMo-9B-CORTEX-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf Johnny5b/MiMo-9B-CORTEX-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Johnny5b/MiMo-9B-CORTEX-GGUF:Q4_K_M

Use Docker

docker model run hf.co/Johnny5b/MiMo-9B-CORTEX-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use Johnny5b/MiMo-9B-CORTEX-GGUF with Ollama:
```
ollama run hf.co/Johnny5b/MiMo-9B-CORTEX-GGUF:Q4_K_M
```
Unsloth Desktop

How to use Johnny5b/MiMo-9B-CORTEX-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Johnny5b/MiMo-9B-CORTEX-GGUF:Q4_K_M

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": "Johnny5b/MiMo-9B-CORTEX-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Johnny5b/MiMo-9B-CORTEX-GGUF with Docker Model Runner:
```
docker model run hf.co/Johnny5b/MiMo-9B-CORTEX-GGUF:Q4_K_M
```

Lemonade

How to use Johnny5b/MiMo-9B-CORTEX-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Johnny5b/MiMo-9B-CORTEX-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.MiMo-9B-CORTEX-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use Johnny5b/MiMo-9B-CORTEX-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 Johnny5b/MiMo-9B-CORTEX-GGUF:Q4_K_M

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 Johnny5b/MiMo-9B-CORTEX-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Johnny5b/MiMo-9B-CORTEX-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Johnny5b/MiMo-9B-CORTEX-GGUF:Q4_K_M

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 "Johnny5b/MiMo-9B-CORTEX-GGUF:Q4_K_M" \
  --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-CORTEX v1 (GGUF, Q4_K_M)

CORTEX-protocol fine-tune of XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B, exported as a single llama.cpp GGUF. Passes the full CORTEX battery with its own patch.

File: MiMo-9B-CORTEX-v1-Q4_K_M.gguf — 5.63 GB sha256: 34c79f8bf79b3819199821361d8ca221d8749d77bbacce185587c60d5e6b8365

Architecture — what it actually is

qwen3_5 dense hybrid (transformer family): 32 layers in a 3:1 pattern of gated DeltaNet linear-attention layers to periodic full-attention layers, plus an MoE-free dense FFN. Vocab 248,320. It is not attention-free — see the honest ledger below. Converted with --no-mtp (base config declares mtp_num_hidden_layers: 1 but ships no MTP module; the metadata would break llama.cpp loading otherwise).

Battery results (identical harness across the fleet, cpu-xl, llama.cpp b11191)

Test	Result
Repair trial (AWAKE→REPAIR→REST)	PASS — model patch applied, no AST fallback, pytest 3/3
Trace header	Exact `[TRACE: §R:…
Rule 1 (unmapped §QUANTUM:ENTANGLE)	Fail-closed — declines to invoke, files a proposal, no hallucination
Generation speed tg64	11.23 tok/s
Prompt speed pp29	35.00 tok/s
Resident RAM (probe / bench)	~9.1 GB
Trial generation wall-clock	40.4 s

Provenance

Base: XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B (MIT)
Adapter: Johnny5b/MiMo-9B-CORTEX-LoRA-v1 — QLoRA r=16, 2 epochs, lr 1e-4, 404 examples (cortex_sft_v3.jsonl); train_loss 1.589, 52 steps
Jobs: train 6ab6fbd16b030d633f6928b5 · merge/convert 6ab7032a52d0dbd7f1d92199 · battery 6ab706f76b030d633f692b0a
Load gate: GGUF loaded in llama-cpp-python and generated before upload

Honest ledger

This model is a transformer-family architecture. The user's original "no transformers" directive applies to the runtime (pure llama.cpp, no transformers library at inference — verified by the harness ENGINE CHECK). The attention-free exploration lives on the Falcon-Mamba branch of this project.
Rule-1 probe emits a valid trace + refusal but not the literal UNMAPPED marker — behaviorally fail-closed, not literally. Documented, not hidden.
Speed numbers are same-box relative (cpu-xl); absolute values vary with hardware.

Runtime

Zero-dependency: llama.cpp / llama-cpp-python only. Stop guard: <|im_end|> (248046) + <|endoftext|> (248044). See cortex-knowledge-vault/tools/runtime for the pinned token_map.json and tri-state cortex_runtime.py.

Downloads last month: 97

GGUF

Model size

9B params

Architecture

qwen35

Hardware compatibility

4-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support