Instructions to use microtensor-archive/mt-code-3g-r1236-5EXH1GnJ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use microtensor-archive/mt-code-3g-r1236-5EXH1GnJ 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 microtensor-archive/mt-code-3g-r1236-5EXH1GnJ
# Run inference directly in the terminal:
llama cli -hf microtensor-archive/mt-code-3g-r1236-5EXH1GnJ

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf microtensor-archive/mt-code-3g-r1236-5EXH1GnJ
# Run inference directly in the terminal:
llama cli -hf microtensor-archive/mt-code-3g-r1236-5EXH1GnJ

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 microtensor-archive/mt-code-3g-r1236-5EXH1GnJ
# Run inference directly in the terminal:
./llama-cli -hf microtensor-archive/mt-code-3g-r1236-5EXH1GnJ

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 microtensor-archive/mt-code-3g-r1236-5EXH1GnJ
# Run inference directly in the terminal:
./build/bin/llama-cli -hf microtensor-archive/mt-code-3g-r1236-5EXH1GnJ

Use Docker

docker model run hf.co/microtensor-archive/mt-code-3g-r1236-5EXH1GnJ

LM Studio
Jan
Ollama
How to use microtensor-archive/mt-code-3g-r1236-5EXH1GnJ with Ollama:
```
ollama run hf.co/microtensor-archive/mt-code-3g-r1236-5EXH1GnJ
```

Unsloth Studio

How to use microtensor-archive/mt-code-3g-r1236-5EXH1GnJ with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for microtensor-archive/mt-code-3g-r1236-5EXH1GnJ to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for microtensor-archive/mt-code-3g-r1236-5EXH1GnJ to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for microtensor-archive/mt-code-3g-r1236-5EXH1GnJ to start chatting

How to use microtensor-archive/mt-code-3g-r1236-5EXH1GnJ with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf microtensor-archive/mt-code-3g-r1236-5EXH1GnJ

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": "microtensor-archive/mt-code-3g-r1236-5EXH1GnJ"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use microtensor-archive/mt-code-3g-r1236-5EXH1GnJ with Docker Model Runner:
```
docker model run hf.co/microtensor-archive/mt-code-3g-r1236-5EXH1GnJ
```

Lemonade

How to use microtensor-archive/mt-code-3g-r1236-5EXH1GnJ with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull microtensor-archive/mt-code-3g-r1236-5EXH1GnJ

Run and chat with the model

lemonade run user.mt-code-3g-r1236-5EXH1GnJ-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use microtensor-archive/mt-code-3g-r1236-5EXH1GnJ with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf microtensor-archive/mt-code-3g-r1236-5EXH1GnJ

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 microtensor-archive/mt-code-3g-r1236-5EXH1GnJ

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use microtensor-archive/mt-code-3g-r1236-5EXH1GnJ with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf microtensor-archive/mt-code-3g-r1236-5EXH1GnJ

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 "microtensor-archive/mt-code-3g-r1236-5EXH1GnJ" \
  --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"

Microtensor archive · code/mt-3g · round 1236

This repository is an archival copy of a system submitted to the Microtensor subnet (Bittensor netuid 92) and certified by its validators. The figures below were measured by the network on reference hardware. They are not self-reported.

Miner hotkey: 5EXH1GnJCQjij9zeLZPqQ9KRnHhmAwWvj4Wxh4Tm7HTpUiB6
System digest: a382223b21c2ee067cdaf67f0d7e5021
Arena: code / mt-3g
Round: 1236
Standing this round: unmeasured

Measured record

Quality: 0.0
Expected cost: 0.0 ms per query
Replication: 1
Config hash: sha256:529c3abd98a5d09d5b6ca50560eb654fa86a97ed10846b92f12f67aefa4dc7f5
Reports root: sha256:c867fe89b3af4ba7524e5173bc7cd6c54e6aa7c8145dbc7f57b5dfb1e3d31b2b

The full signed record is in certificate.json. It is recomputable from the round's published reports.

The artifact was fetched over a scheme that left no manifest file on disk; the bytes here are the component the network verified by digest and measured, retained without the submitted manifest.

Downloads last month: 8

GGUF

Model size

2B params

Architecture

qwen3

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Inference Providers NEW

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