Instructions to use dasLOL/mt-support-3g-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use dasLOL/mt-support-3g-v2 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 dasLOL/mt-support-3g-v2
# Run inference directly in the terminal:
llama cli -hf dasLOL/mt-support-3g-v2

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf dasLOL/mt-support-3g-v2
# Run inference directly in the terminal:
llama cli -hf dasLOL/mt-support-3g-v2

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 dasLOL/mt-support-3g-v2
# Run inference directly in the terminal:
./build/bin/llama cli -hf dasLOL/mt-support-3g-v2

Use Docker

docker model run hf.co/dasLOL/mt-support-3g-v2

Llama new
LM Studio
Jan
Ollama
How to use dasLOL/mt-support-3g-v2 with Ollama:
```
ollama run hf.co/dasLOL/mt-support-3g-v2
```
Unsloth Desktop

How to use dasLOL/mt-support-3g-v2 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf dasLOL/mt-support-3g-v2

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": "dasLOL/mt-support-3g-v2"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use dasLOL/mt-support-3g-v2 with Docker Model Runner:
```
docker model run hf.co/dasLOL/mt-support-3g-v2
```

Lemonade

How to use dasLOL/mt-support-3g-v2 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull dasLOL/mt-support-3g-v2

Run and chat with the model

lemonade run user.mt-support-3g-v2-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use dasLOL/mt-support-3g-v2 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf dasLOL/mt-support-3g-v2

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 dasLOL/mt-support-3g-v2

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use dasLOL/mt-support-3g-v2 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf dasLOL/mt-support-3g-v2

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 "dasLOL/mt-support-3g-v2" \
  --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"

dasLOL commited on Sep 12

Commit

1044cd0

verified ·

1 Parent(s): 70be62c

manifest for round 1240

Browse files

Files changed (1) hide show

manifest.json +1 -1

manifest.json CHANGED Viewed

@@ -1 +1 @@

- {"artifact_digest":"sha256:6c4f06ddf4105f749facdfaaf795367d498a38c15f398b22e14e05b6f0aa7265","declared":{"p95_latency_ms":15000,"peak_rss_bytes":3221225472,"size_bytes":986049152},"files":[{"digest":"sha256:11c1242468b98829901bf536e9a9bd4809188db8eb9a8131519462b811c26c6c","path":"model.gguf","size_bytes":986049152}],"hardware_class":"mt-3g","hotkey":"5Hdx6xd7atKCuUAbPivohUtkSJT9xwjywj4BSjhDHA7AgHLw","load":{"base_model":"Qwen/Qwen3-0.6B@c1899de289a04d12100db370d81485cdf75e47ca","entrypoint":"model.gguf","format":"gguf","max_input":{"tokens":512},"preprocessing":{},"quantization":"Q8_0"},"round_index":1240,"sealed":null,"signature":"~~9a55de3a02b0175c4169bc5895101e9070f856457870e95fc68e58c0f46c01400e87985f1316fd03a0ace74457e2fe6e0b1eaf8dc274dd59730608bc84340d8b~~","source":"https:huggingface.co/dasLOL/mt-support-3g-v2/resolve/main","system":null,"track":"support","version":"0.4.0"}

+ {"artifact_digest":"sha256:6c4f06ddf4105f749facdfaaf795367d498a38c15f398b22e14e05b6f0aa7265","declared":{"p95_latency_ms":15000,"peak_rss_bytes":3221225472,"size_bytes":986049152},"files":[{"digest":"sha256:11c1242468b98829901bf536e9a9bd4809188db8eb9a8131519462b811c26c6c","path":"model.gguf","size_bytes":986049152}],"hardware_class":"mt-3g","hotkey":"5Hdx6xd7atKCuUAbPivohUtkSJT9xwjywj4BSjhDHA7AgHLw","load":{"base_model":"Qwen/Qwen3-0.6B@c1899de289a04d12100db370d81485cdf75e47ca","entrypoint":"model.gguf","format":"gguf","max_input":{"tokens":512},"preprocessing":{},"quantization":"Q8_0"},"round_index":1240,"sealed":null,"signature":"48f73392844438334456ea61ace356a2e23ce788de05d58479284b5496e0214e9d200802762144deccbe6594f7c1d518453fccde33166845b5aa7b793cfd2581","source":"https:huggingface.co/dasLOL/mt-support-3g-v2/resolve/main","system":null,"track":"support","version":"0.4.0"}