Instructions to use nicolasramos/odooclaw-medium-2.6b-ft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use nicolasramos/odooclaw-medium-2.6b-ft 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 nicolasramos/odooclaw-medium-2.6b-ft:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf nicolasramos/odooclaw-medium-2.6b-ft:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf nicolasramos/odooclaw-medium-2.6b-ft:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf nicolasramos/odooclaw-medium-2.6b-ft: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 nicolasramos/odooclaw-medium-2.6b-ft:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf nicolasramos/odooclaw-medium-2.6b-ft: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 nicolasramos/odooclaw-medium-2.6b-ft:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf nicolasramos/odooclaw-medium-2.6b-ft:Q4_K_M

Use Docker

docker model run hf.co/nicolasramos/odooclaw-medium-2.6b-ft:Q4_K_M

LM Studio
Jan

vLLM

How to use nicolasramos/odooclaw-medium-2.6b-ft with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nicolasramos/odooclaw-medium-2.6b-ft"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nicolasramos/odooclaw-medium-2.6b-ft",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nicolasramos/odooclaw-medium-2.6b-ft:Q4_K_M

Ollama
How to use nicolasramos/odooclaw-medium-2.6b-ft with Ollama:
```
ollama run hf.co/nicolasramos/odooclaw-medium-2.6b-ft:Q4_K_M
```
Unsloth Desktop

How to use nicolasramos/odooclaw-medium-2.6b-ft with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf nicolasramos/odooclaw-medium-2.6b-ft: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": "nicolasramos/odooclaw-medium-2.6b-ft:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use nicolasramos/odooclaw-medium-2.6b-ft with Docker Model Runner:
```
docker model run hf.co/nicolasramos/odooclaw-medium-2.6b-ft:Q4_K_M
```

Lemonade

How to use nicolasramos/odooclaw-medium-2.6b-ft with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull nicolasramos/odooclaw-medium-2.6b-ft:Q4_K_M

Run and chat with the model

lemonade run user.odooclaw-medium-2.6b-ft-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use nicolasramos/odooclaw-medium-2.6b-ft with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf nicolasramos/odooclaw-medium-2.6b-ft: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 nicolasramos/odooclaw-medium-2.6b-ft:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use nicolasramos/odooclaw-medium-2.6b-ft with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf nicolasramos/odooclaw-medium-2.6b-ft: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 "nicolasramos/odooclaw-medium-2.6b-ft: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"

OdooClaw Medium 2.6B FT

The on-device agentic model for Odoo — the best quality-to-speed tradeoff in the OdooClaw family.

Fine-tuned LFM2.5-2.6B (Liquid AI) for tool calling inside Odoo (ERP) via MCP. Ask in natural language in the Odoo chat and the model picks the right Odoo tool. Current version: v18 (2026-08-19) — the definitive model of the Medium line.

Part of the OdooClaw collection. The MLX release (Apple Silicon) is odooclaw-medium-2.6b-ft-mlx.

Why this model

The Medium is the agentic sweet spot of the OdooClaw family:

LFM2.5-2.6B (this model, fine-tuned): the "on-device agentic" model of the LFM2.5 family — reasons before every tool call
Light 1.2B (odooclaw-light-1.2b-ft): faster and lighter, but lower accuracy on business/finance tasks
Medium 2.6B (this model): 94.2% conversation, 99.5% creation on 1000-case batteries — the most balanced model of the series

We deliberately chose the 2.6B for agentic workloads where the model reasons before every tool call — the extra accuracy is worth the small latency cost.

⭐ Evaluation results (v18, 1000-case batteries)

Battery (1000)	v18
Conversation (990)	94.2%
Creation (1000)	99.5%
Business (1000)	74.0%
Invoices (1000)	71.6%

The v18 is the most balanced model of the series: top-2 in all 4 categories at once, no tradeoffs. Trained with balanced distribution (matches evaluation) and natural variety.

🚀 Hardware performance (v18, Q4_K_M)

Mac Mini M4 (MLX 4-bit)

Test	Time	Speed
Tool call (find partner)	0.98s	—
Long text (200 tok)	3.24s	61.7 tok/s

📦 Formats

odooclaw-medium-2.6b-ft-Q4_K_M.gguf odooclaw-medium-2.6b-ft-mlx (Apple Silicon, 4-bit) Modelfile

🔧 Quick deploy

# llama.cpp
llama-server -m odooclaw-medium-2.6b-ft-Q4_K_M.gguf \
  --chat-template-file chat-template-medium-no-think.jinja \
  --temp 0.0 --jinja

# Ollama
ollama create odooclaw-medium -f Modelfile

📚 Training

LiquidAI/LFM2.5-2.6B train_lfm25_26b.py

Chat template

4-bit

License

Apache 2.0 — free for everyone, that's the whole point.

Downloads last month: 187

GGUF

Model size

3B params

Architecture

lfm2

Hardware compatibility

4-bit

Model tree for nicolasramos/odooclaw-medium-2.6b-ft

Base model

LiquidAI/LFM2.5-2.6B-Base

Finetuned

LiquidAI/LFM2.5-2.6B

Quantized

(98)

this model

Collection including nicolasramos/odooclaw-medium-2.6b-ft

OdooClaw

Collection

8 items • Updated Sep 1 • 2