Instructions to use aether-models/lars-packs with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use aether-models/lars-packs 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 aether-models/lars-packs
# Run inference directly in the terminal:
llama cli -hf aether-models/lars-packs

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf aether-models/lars-packs
# Run inference directly in the terminal:
llama cli -hf aether-models/lars-packs

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 aether-models/lars-packs
# Run inference directly in the terminal:
./llama-cli -hf aether-models/lars-packs

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 aether-models/lars-packs
# Run inference directly in the terminal:
./build/bin/llama-cli -hf aether-models/lars-packs

Use Docker

docker model run hf.co/aether-models/lars-packs

LM Studio
Jan
Ollama
How to use aether-models/lars-packs with Ollama:
```
ollama run hf.co/aether-models/lars-packs
```
Unsloth Desktop

How to use aether-models/lars-packs with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf aether-models/lars-packs

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": "aether-models/lars-packs"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use aether-models/lars-packs with Docker Model Runner:
```
docker model run hf.co/aether-models/lars-packs
```

Lemonade

How to use aether-models/lars-packs with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull aether-models/lars-packs

Run and chat with the model

lemonade run user.lars-packs-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use aether-models/lars-packs with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf aether-models/lars-packs

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 aether-models/lars-packs

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use aether-models/lars-packs with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf aether-models/lars-packs

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 "aether-models/lars-packs" \
  --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"

lars packs

Private backup of the lars-sdk dev packs. They were rebuilt on 2026-10-08 and 09, after the machine that held the originals died. Each pack is in packs/<name>/<version>/:

model.gguf: the fused LoRA model, imatrix-quantized.
calibration.json: the calibrator, fitted on 4,120 jev-bench validation rows.
pack.json: the manifest, with the base, the llama.cpp commit, sha256 sums and per-config scores.

Scores are on the jev-bench test split (22 configs, 200 rows each), through the pack:

Pack	Base, checkpoint	Quant	Macro accuracy	Macro Brier	Lost original
`lars-0.6b-dev` 0.0.2	Qwen/Qwen3-0.6B, final step 4,449	Q4_K_M	0.637	0.418	0.650 / 0.419
`lars-0.6b-dev-step2500` 0.0.2	Qwen/Qwen3-0.6B, step 2,500 (selected)	Q4_K_M	0.625	0.433
`lars-2b-dev` 0.0.1	Qwen/Qwen3.5-2B, final step 5,370	Q4_K_M	0.713	0.331	0.716 / 0.333

Training: LoRA on corpus E. The 2B also trained on the typed-decisions train split; it scores 0.757 on that benchmark's test split, against 0.759 for the lost pack.
The step-2,500 pack: kept for comparison. The packs build from the final step.
lars-8b-dev 0.0.2 (Qwen/Qwen3-8B, Q3_K_M, was 0.748) is not rebuilt yet. It needs a machine with more than 64 GB; lars-sdk's HANDOFF.md has the steps.

Apache-2.0, like the base models.

Downloads last month: 88

GGUF

Model size

0.6B 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