Leanstral-1.5-119B-A6B-GGUF

Instructions to use servantofares/Leanstral-1.5-119B-A6B-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 servantofares/Leanstral-1.5-119B-A6B-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 servantofares/Leanstral-1.5-119B-A6B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf servantofares/Leanstral-1.5-119B-A6B-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 servantofares/Leanstral-1.5-119B-A6B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf servantofares/Leanstral-1.5-119B-A6B-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 servantofares/Leanstral-1.5-119B-A6B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf servantofares/Leanstral-1.5-119B-A6B-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 servantofares/Leanstral-1.5-119B-A6B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf servantofares/Leanstral-1.5-119B-A6B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/servantofares/Leanstral-1.5-119B-A6B-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use servantofares/Leanstral-1.5-119B-A6B-GGUF with Ollama:
```
ollama run hf.co/servantofares/Leanstral-1.5-119B-A6B-GGUF:Q4_K_M
```
Unsloth Desktop

How to use servantofares/Leanstral-1.5-119B-A6B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf servantofares/Leanstral-1.5-119B-A6B-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": "servantofares/Leanstral-1.5-119B-A6B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use servantofares/Leanstral-1.5-119B-A6B-GGUF with Docker Model Runner:
```
docker model run hf.co/servantofares/Leanstral-1.5-119B-A6B-GGUF:Q4_K_M
```

Lemonade

How to use servantofares/Leanstral-1.5-119B-A6B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull servantofares/Leanstral-1.5-119B-A6B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Leanstral-1.5-119B-A6B-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use servantofares/Leanstral-1.5-119B-A6B-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 servantofares/Leanstral-1.5-119B-A6B-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 servantofares/Leanstral-1.5-119B-A6B-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use servantofares/Leanstral-1.5-119B-A6B-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf servantofares/Leanstral-1.5-119B-A6B-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 "servantofares/Leanstral-1.5-119B-A6B-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"

Leanstral 1.5 models, quantized.

I don't want to waste your time reading a 500-word LLM-generated essay on what the model is, when Mistral themselves already provide a good explanation in the original model's README. Go read that instead.

Instead, I'll focus on the important part: why should you use my quantization?

Properly labeled as mistral4 architecture instead of deepseek2. This is a bug in upstream llama.cpp's GGUF conversion code. PR incoming.
Chat template from Leanstral-2603 embedded inside GGUF, no need to specify a template by yourself.
I run these models myself on my Strix Halo box.
You can interrogate me on the Lean Zulip if you find these quants to be malicious, or if you just have suggestions for improvements.

Enjoy!

Downloads last month: 60

GGUF

Model size

119B params

Architecture

mistral4

Hardware compatibility

4-bit

6-bit

16-bit

Inference Providers NEW

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

Model tree for servantofares/Leanstral-1.5-119B-A6B-GGUF

Base model

mistralai/Leanstral-2603

Finetuned

mistralai/Leanstral-1.5-119B-A6B

Quantized

(14)

this model