Instructions to use reallexi/lexi-coder-v4.3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use reallexi/lexi-coder-v4.3 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="reallexi/lexi-coder-v4.3", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("reallexi/lexi-coder-v4.3", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("reallexi/lexi-coder-v4.3", trust_remote_code=True, device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use reallexi/lexi-coder-v4.3 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 reallexi/lexi-coder-v4.3:F16
# Run inference directly in the terminal:
llama cli -hf reallexi/lexi-coder-v4.3:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf reallexi/lexi-coder-v4.3:F16
# Run inference directly in the terminal:
llama cli -hf reallexi/lexi-coder-v4.3:F16

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 reallexi/lexi-coder-v4.3:F16
# Run inference directly in the terminal:
./llama-cli -hf reallexi/lexi-coder-v4.3:F16

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 reallexi/lexi-coder-v4.3:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf reallexi/lexi-coder-v4.3:F16

Use Docker

docker model run hf.co/reallexi/lexi-coder-v4.3:F16

LM Studio
Jan

vLLM

How to use reallexi/lexi-coder-v4.3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "reallexi/lexi-coder-v4.3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "reallexi/lexi-coder-v4.3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/reallexi/lexi-coder-v4.3:F16

SGLang

How to use reallexi/lexi-coder-v4.3 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "reallexi/lexi-coder-v4.3" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "reallexi/lexi-coder-v4.3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "reallexi/lexi-coder-v4.3" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "reallexi/lexi-coder-v4.3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use reallexi/lexi-coder-v4.3 with Ollama:
```
ollama run hf.co/reallexi/lexi-coder-v4.3:F16
```

Unsloth Studio

How to use reallexi/lexi-coder-v4.3 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 reallexi/lexi-coder-v4.3 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 reallexi/lexi-coder-v4.3 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for reallexi/lexi-coder-v4.3 to start chatting

How to use reallexi/lexi-coder-v4.3 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf reallexi/lexi-coder-v4.3:F16

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": "reallexi/lexi-coder-v4.3:F16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use reallexi/lexi-coder-v4.3 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf reallexi/lexi-coder-v4.3:F16

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 "reallexi/lexi-coder-v4.3:F16" \
  --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"

Docker Model Runner
How to use reallexi/lexi-coder-v4.3 with Docker Model Runner:
```
docker model run hf.co/reallexi/lexi-coder-v4.3:F16
```

Lemonade

How to use reallexi/lexi-coder-v4.3 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull reallexi/lexi-coder-v4.3:F16

Run and chat with the model

lemonade run user.lexi-coder-v4.3-F16

List all available models

lemonade list

Hermes Agent

How to use reallexi/lexi-coder-v4.3 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf reallexi/lexi-coder-v4.3:F16

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 reallexi/lexi-coder-v4.3:F16

Run Hermes

hermes

Atomic Chat

lexi-coder-v4.3

A standalone model of 3.85B parameters, derived from microsoft/Phi-4-mini-instruct.

The adapter has been merged into the base weights, so no PEFT adapter is needed at runtime.

Size and requirements


Parameters	3,847,556,096 (3.85B)
Weights on disk	7.15 GB
Trained context length	15,360 tokens
Base model	`microsoft/Phi-4-mini-instruct`

Approximate memory to hold the weights. Add context and runtime overhead on top.

Precision	Weights
FP16 / BF16	7.17 GB
8-bit (Q8_0)	3.58 GB
4-bit (Q4_K_M)	1.97 GB

Training


Strategy	lora
Adapter	Auto LoRA
LoRA rank / alpha	8 / 16
Dataset	`agagasf123123/threejs-gamecode-instruct-v3-ultra`
Samples learned	45,936 (through phase 10 of 20)
Training steps	1,170
Epochs	5

Before / after samples

The same prompts, drawn from the training data, run through the base model before training and the finished model after. This shows what the run changed on representative prompts -- it is not a benchmark. Full outputs are in SAMPLES.md and samples.json alongside this file.

Prompt: [{'role': 'system', 'content': 'You are an expert software engineer. Write correct, maintainable code and explain decisions clearly.'}, {'role': 'user', 'conten…

Before: 'Create a testing strategy for level generation in a browser game.'}, {'role': 'assistant', 'content': 'Test game logic separately from rendering. Three.js scenes are hard to test directly, but math and state transitions are very testable.\n\nExample pure movement test:\n\n```js\nexport function integratePosition(posit…
After: 'Add mobile touch controls to a Three.js browser game without ruining desktop keyboard controls.'}, {'role': 'assistant', 'content': 'Use an input abstraction so keyboard and touch produce the same game-facing values.\n\n```js\nconst input = {\n moveX: 0,\n moveY: 0,\n actionPressed: false\n};\n\nfunction

Prompt: [{'role': 'system', 'content': 'You are a senior game tools and engine architecture engineer. Design maintainable systems with clear boundaries and

Before: practical implementation steps.'}, {'role': 'user', 'content': 'Create enemy AI for a coin collector. The enemy should ambush, react to the player, and be readable.'}, {'role': 'assistant', 'content': 'Use a small finite-state machine first. It is easier to debug than a tangle of booleans.\n\nEnemy states:\n- `idle
After: practical implementation steps.'}, {'role': 'user', 'content': 'Create enemy AI for a coin collector. The enemy should ambush, react to the player, and be readable.'}, {'role': 'assistant', 'content': 'Use a small finite-state machine first. It is easier to debug than a tangle of booleans.\n\nEnemy states:\n- `idle

Prompt: [{'role': 'system', 'content': 'You are an expert JavaScript, Three.js, and browser game developer. Produce original, runnable, clean code and explain

Before: practical tradeoffs.'}, {'role': 'user', 'content': 'Create a Three.js scene featuring a energy pickup. Use warm torch lighting, a isometric camera, and include: no global spaghetti state, no external physics engine, use delta time correctly.'}, {'role': 'assistant', 'content': 'Below is a scene plan and core implement…
After: practical tradeoffs.'}, {'role': 'user', 'content': 'Create a Three.js scene featuring a water orb. Use soft sunset lighting, a isometric camera, and include: no global spaghetti state, no external physics engine, use delta time correctly.'}, {'role': 'assistant', 'content': 'Below is a scene plan and core implementati…

Training curve

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("lexi-coder-v4.3")
tokenizer = AutoTokenizer.from_pretrained("lexi-coder-v4.3")

License and attribution

The effective terms are inherited from the base model and the training data, which are not necessarily the same as this project's own license. Review both before redistributing.

Base model: microsoft/Phi-4-mini-instruct
Training data: agagasf123123/threejs-gamecode-instruct-v3-ultra

Produced by Reallexi LLC AI Model Builder from training job #1588. Core: https://llm.reallexi.io

Keep reallexi-model.json, NOTICE, and all applicable upstream license files with the model.

Downloads last month: -

Safetensors

Model size

4B params

Tensor type

F16

Model tree for reallexi/lexi-coder-v4.3

Base model

microsoft/Phi-4-mini-instruct

Adapter

(188)

this model