Instructions to use Berkelium-ai/BerkeliumGPT-Coder-3b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Berkelium-ai/BerkeliumGPT-Coder-3b with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("Berkelium-ai/BerkeliumGPT-Coder-3b")

prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True
)

text = generate(model, tokenizer, prompt=prompt, verbose=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use Berkelium-ai/BerkeliumGPT-Coder-3b with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "Berkelium-ai/BerkeliumGPT-Coder-3b"

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "Berkelium-ai/BerkeliumGPT-Coder-3b"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Berkelium-ai/BerkeliumGPT-Coder-3b with Hermes Agent:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "Berkelium-ai/BerkeliumGPT-Coder-3b"

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 Berkelium-ai/BerkeliumGPT-Coder-3b

Run Hermes

hermes

OpenClaw new

How to use Berkelium-ai/BerkeliumGPT-Coder-3b with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "Berkelium-ai/BerkeliumGPT-Coder-3b"

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 "Berkelium-ai/BerkeliumGPT-Coder-3b" \
  --custom-provider-id mlx-lm \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

MLX LM

How to use Berkelium-ai/BerkeliumGPT-Coder-3b with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "Berkelium-ai/BerkeliumGPT-Coder-3b"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "Berkelium-ai/BerkeliumGPT-Coder-3b"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "Berkelium-ai/BerkeliumGPT-Coder-3b",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

🚀 BerkeliumGPT-Coder-3B

Production-Grade Agentic Coding Model

Built for software engineering, code generation, debugging, repository understanding, and autonomous coding workflows.

Quick Start

Transformers

from transformers import AutoTokenizer, AutoModelForCausalLM

model_id = "berkelium-ai/BerkeliumGPT-Coder-3B"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype="auto"
)

MLX

mlx_lm.generate \
  --model berkelium-ai/BerkeliumGPT-Coder-3B \
  --prompt "Build a FastAPI backend."

Docker Model Runner

docker model pull hf.co/berkelium-ai/BerkeliumGPT-Coder-3B

docker model run hf.co/berkelium-ai/BerkeliumGPT-Coder-3B

Ollama (GGUF Release)

ollama run berkeliumgpt-coder

Model Details

Property	Value
Model Name	BerkeliumGPT-Coder-3B
Base Model	Qwen2.5-3B-Instruct
Parameters	3 Billion
Architecture	Transformer Decoder
Domain	Software Engineering
Context Length	Base Model Configuration
License	Apache-2.0

Capabilities

Code Generation
Agentic Coding
Repository Analysis
Bug Detection
Refactoring
Test Generation
Documentation Writing
API Development
DevOps Automation

Supported Languages

Python
JavaScript
TypeScript
Go
Rust
Java
C++
C#
SQL
Bash
HTML
CSS

Example Prompt

User

Build a FastAPI application with JWT authentication and PostgreSQL.

Assistant

Generates:

Backend API
Database models
Authentication system
Docker configuration
Unit tests

Intended Use

BerkeliumGPT-Coder-3B is designed for:

AI Coding Assistants
Software Engineering Agents
Developer Copilots
Research
Local Inference
Autonomous Development Workflows

Limitations

Generated code should be reviewed before production deployment.
Security auditing is recommended.
Human validation remains essential.

License

Apache-2.0

Downloads last month: 70

Safetensors

Model size

2B params

Tensor type

BF16

MLX

Hardware compatibility

Quantized

Model tree for Berkelium-ai/BerkeliumGPT-Coder-3b

Base model

Qwen/Qwen2.5-3B

Finetuned

Qwen/Qwen2.5-3B-Instruct

Finetuned

(1409)

this model

Quantizations

2 models

Berkelium-ai
/

BerkeliumGPT-Coder-3b

🚀 BerkeliumGPT-Coder-3B

Quick Start

Transformers

MLX

Docker Model Runner

Ollama (GGUF Release)

Model Details

Capabilities

Supported Languages

Example Prompt

Intended Use

Limitations

License

Model tree for Berkelium-ai/BerkeliumGPT-Coder-3b

Dataset used to train Berkelium-ai/BerkeliumGPT-Coder-3b