Instructions to use peterjohannmedina/Medina-Qwen3-14B-OpenClaw with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use peterjohannmedina/Medina-Qwen3-14B-OpenClaw with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("peterjohannmedina/Medina-Qwen3-14B-OpenClaw", dtype="auto")

PEFT
How to use peterjohannmedina/Medina-Qwen3-14B-OpenClaw with PEFT:
```
Task type is invalid.
```

llama-cpp-python

How to use peterjohannmedina/Medina-Qwen3-14B-OpenClaw with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="peterjohannmedina/Medina-Qwen3-14B-OpenClaw",
	filename="Medina-Qwen3-14B-OpenClaw-Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use peterjohannmedina/Medina-Qwen3-14B-OpenClaw with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf peterjohannmedina/Medina-Qwen3-14B-OpenClaw:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf peterjohannmedina/Medina-Qwen3-14B-OpenClaw:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf peterjohannmedina/Medina-Qwen3-14B-OpenClaw:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf peterjohannmedina/Medina-Qwen3-14B-OpenClaw: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 peterjohannmedina/Medina-Qwen3-14B-OpenClaw:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf peterjohannmedina/Medina-Qwen3-14B-OpenClaw: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 peterjohannmedina/Medina-Qwen3-14B-OpenClaw:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf peterjohannmedina/Medina-Qwen3-14B-OpenClaw:Q4_K_M

Use Docker

docker model run hf.co/peterjohannmedina/Medina-Qwen3-14B-OpenClaw:Q4_K_M

LM Studio
Jan
Ollama
How to use peterjohannmedina/Medina-Qwen3-14B-OpenClaw with Ollama:
```
ollama run hf.co/peterjohannmedina/Medina-Qwen3-14B-OpenClaw:Q4_K_M
```

Unsloth Studio

How to use peterjohannmedina/Medina-Qwen3-14B-OpenClaw 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 peterjohannmedina/Medina-Qwen3-14B-OpenClaw 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 peterjohannmedina/Medina-Qwen3-14B-OpenClaw to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for peterjohannmedina/Medina-Qwen3-14B-OpenClaw to start chatting

How to use peterjohannmedina/Medina-Qwen3-14B-OpenClaw with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf peterjohannmedina/Medina-Qwen3-14B-OpenClaw:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "peterjohannmedina/Medina-Qwen3-14B-OpenClaw:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use peterjohannmedina/Medina-Qwen3-14B-OpenClaw with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf peterjohannmedina/Medina-Qwen3-14B-OpenClaw: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 peterjohannmedina/Medina-Qwen3-14B-OpenClaw:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use peterjohannmedina/Medina-Qwen3-14B-OpenClaw with Docker Model Runner:
```
docker model run hf.co/peterjohannmedina/Medina-Qwen3-14B-OpenClaw:Q4_K_M
```

Lemonade

How to use peterjohannmedina/Medina-Qwen3-14B-OpenClaw with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull peterjohannmedina/Medina-Qwen3-14B-OpenClaw:Q4_K_M

Run and chat with the model

lemonade run user.Medina-Qwen3-14B-OpenClaw-Q4_K_M

List all available models

lemonade list

Medina-Qwen3-14B-OpenClaw

A LoRA fine-tune of TeichAI/Qwen3-14B-Claude-4.5-Opus-High-Reasoning-Distill trained on OpenClaw tool-call data — optimized for agentic reasoning with structured tool invocation.

The base model is itself a Claude 4.5 Opus high-reasoning distillation of Qwen3-14B, making this a compact but capable agent model that runs comfortably on consumer hardware (M3 MacBook Pro, single 24GB GPU).

GGUF Downloads

Quantization	Size	Use case
Q4_K_M	8.4 GB	✅ Recommended — runs on M3 MacBook, 16GB+ RAM
Q8_0	14.6 GB	Near-lossless, 24GB VRAM or 32GB unified memory

Training Details

Parameter	Value
Base model	TeichAI/Qwen3-14B-Claude-4.5-Opus-High-Reasoning-Distill
Training GPU	NVIDIA RTX 4090 (24GB)
Framework	Unsloth + TRL SFTTrainer
Dataset	OpenClaw tool-call examples (250 examples)
Epochs	3
LoRA rank	r=32, alpha=64, rsLoRA=True
LoRA dropout	0.05
LoRA targets	q/k/v/o/gate/up/down proj
Context window	4096 tokens
Batch size	2 (effective: 16 with grad accum)
Learning rate	2e-4 (cosine schedule, 5% warmup)
Quantization	4-bit NF4 during training
Optimizer	AdamW 8-bit

What It Does

This adapter teaches the model the OpenClaw tool-calling format — a structured XML-style invocation pattern used by the OpenClaw AI agent platform:

<function_calls>
<invoke name="TOOL_NAME">
<parameter name="PARAM_NAME">value</parameter>
</invoke>
</function_calls>

Supported tools in training data: exec, read, write, edit, web_search, web_fetch, browser, memory_search, memory_get, message, cron, nodes, image, pdf, sessions_spawn, session_status

Usage with llama.cpp / Ollama

# Ollama (Q4_K_M)
ollama run hf.co/peterjohannmedina/Medina-Qwen3-14B-OpenClaw:Q4_K_M

# llama.cpp direct
./llama-cli -m Medina-Qwen3-14B-OpenClaw-Q4_K_M.gguf \
  --ctx-size 4096 -p "You are an AI assistant with access to tools..."

Usage with Transformers (LoRA adapter)

from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
import torch

base = AutoModelForCausalLM.from_pretrained(
    "TeichAI/Qwen3-14B-Claude-4.5-Opus-High-Reasoning-Distill",
    torch_dtype=torch.bfloat16,
    device_map="auto",
)
model = PeftModel.from_pretrained(base, "peterjohannmedina/Medina-Qwen3-14B-OpenClaw")
tokenizer = AutoTokenizer.from_pretrained("peterjohannmedina/Medina-Qwen3-14B-OpenClaw")

Companion Model

For a larger, more capable version trained on the same dataset:

Medina-Qwen3.5-27B-OpenClaw (Q4_K_M: 15.4 GB, Q8_0: 26.6 GB)

License

Apache 2.0 — same as the base model.

Downloads last month: 120

GGUF

Model size

15B params

Architecture

qwen3

Hardware compatibility

4-bit

8-bit

Inference Providers NEW

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

Model tree for peterjohannmedina/Medina-Qwen3-14B-OpenClaw

Base model

Qwen/Qwen3-14B-Base

Finetuned

Qwen/Qwen3-14B

Finetuned

unsloth/Qwen3-14B

Finetuned

TeichAI/Qwen3-14B-Claude-4.5-Opus-High-Reasoning-Distill

Adapter

(1)

this model