Instructions to use LindotAI/Lin-1-Locus with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use LindotAI/Lin-1-Locus with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="LindotAI/Lin-1-Locus") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("LindotAI/Lin-1-Locus") model = AutoModelForCausalLM.from_pretrained("LindotAI/Lin-1-Locus", 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=256) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use LindotAI/Lin-1-Locus 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 LindotAI/Lin-1-Locus:Q8_0 # Run inference directly in the terminal: llama cli -hf LindotAI/Lin-1-Locus:Q8_0
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf LindotAI/Lin-1-Locus:Q8_0 # Run inference directly in the terminal: llama cli -hf LindotAI/Lin-1-Locus:Q8_0
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf LindotAI/Lin-1-Locus:Q8_0 # Run inference directly in the terminal: ./build/bin/llama cli -hf LindotAI/Lin-1-Locus:Q8_0
Use Docker
docker model run hf.co/LindotAI/Lin-1-Locus:Q8_0
- Llama new
- LM Studio
- Jan
- vLLM
How to use LindotAI/Lin-1-Locus with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "LindotAI/Lin-1-Locus" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "LindotAI/Lin-1-Locus", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/LindotAI/Lin-1-Locus:Q8_0
- SGLang
How to use LindotAI/Lin-1-Locus 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 "LindotAI/Lin-1-Locus" \ --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": "LindotAI/Lin-1-Locus", "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 "LindotAI/Lin-1-Locus" \ --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": "LindotAI/Lin-1-Locus", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Ollama
How to use LindotAI/Lin-1-Locus with Ollama:
ollama run hf.co/LindotAI/Lin-1-Locus:Q8_0
- Unsloth Desktop
- Pi
How to use LindotAI/Lin-1-Locus with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf LindotAI/Lin-1-Locus:Q8_0
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:9931/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "LindotAI/Lin-1-Locus:Q8_0" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use LindotAI/Lin-1-Locus with Docker Model Runner:
docker model run hf.co/LindotAI/Lin-1-Locus:Q8_0
- Lemonade
How to use LindotAI/Lin-1-Locus with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull LindotAI/Lin-1-Locus:Q8_0
Run and chat with the model
lemonade run user.Lin-1-Locus-Q8_0
List all available models
lemonade list
- Hermes Agent
How to use LindotAI/Lin-1-Locus with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf LindotAI/Lin-1-Locus:Q8_0
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://127.0.0.1:9931/v1 hermes config set model.default LindotAI/Lin-1-Locus:Q8_0
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use LindotAI/Lin-1-Locus with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf LindotAI/Lin-1-Locus:Q8_0
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://127.0.0.1:9931/v1 \ --custom-model-id "LindotAI/Lin-1-Locus:Q8_0" \ --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"
Install from WinGet (Windows)
winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf LindotAI/Lin-1-Locus:Q8_0# Run inference directly in the terminal:
llama cli -hf LindotAI/Lin-1-Locus:Q8_0Build from source code
git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf LindotAI/Lin-1-Locus:Q8_0# Run inference directly in the terminal:
./build/bin/llama cli -hf LindotAI/Lin-1-Locus:Q8_0Use Docker
docker model run hf.co/LindotAI/Lin-1-Locus:Q8_0Lin-1 Locus
Lin-1 Locus is a 4B-parameter code model from LindotAI, specialized for Rust. It is fine-tuned from Qwen3.5-4B on curated, test-verified Rust data and answers directly (no long reasoning traces), which keeps it fast enough for local use.
Highlights
- Writes idiomatic, compiling Rust: functions, traits, generics, error handling, iterators, unit tests.
- Trained only on code that passed compilation and/or its own tests.
- Strong sampling diversity: high pass@10 makes it a good fit for generate-and-test loops.
- Runs locally: a Q8_0 GGUF is included (~4.5 GB).
Benchmarks
All numbers measured by us with the same harness for every model (Rust ports of the benchmarks; generated code is compiled and run against the tests).
| Model | HumanEval-Rust p@1 / p@10 | MBPP-Rust p@1 / p@10 | Holdout (Rust) | LBPP-Rust |
|---|---|---|---|---|
| Lin-1 Locus (4B) | 73.1 / 86.1 | 63.4 / 73.1 | 58.7 | 27.5 |
| Lin-1 Epsilon Preview (0.5B) | 48.4 / 65.2 | 41.3 / 54.2 | 30.3 | 4.1 |
| Temper 2 Nodel | 73.3 / 81.8 | 64.7 / 70.6 | 55.4 | 26.4 |
| Qwen2.5-Coder-7B-Instruct | 72.4 / 82.6 | 60.5 / 70.0 | โ | โ |
| Qwen3.5-4B (base) | 66.2 / 81.4 | 57.7 / 73.4 | โ | โ |
| Qwen3-4B | 59.8 / 64.8 | 55.6 / 60.6 | โ | โ |
| Qwen2.5-Coder-3B-Instruct | 56.5 / 71.9 | 44.8 / 60.0 | โ | โ |
| Qwen2.5-Coder-1.5B-Instruct | 39.0 / 56.1 | 38.3 / 52.1 | โ | โ |
| Qwen3.5-2B | 31.7 / 51.3 | 36.0 / 53.2 | โ | โ |
Holdout is our private set of Rust tasks with tests that was never used for training.
Quick start
Transformers
from transformers import AutoTokenizer, AutoModelForCausalLM
model_id = "LindotAI/Lin-1-Locus"
tok = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype="auto", device_map="auto")
messages = [{"role": "user", "content": "Write a Rust function that returns the n-th Fibonacci number using u128, with tests."}]
inputs = tok.apply_chat_template(messages, add_generation_prompt=True, enable_thinking=False, return_tensors="pt").to(model.device)
out = model.generate(inputs, max_new_tokens=1024, temperature=0.2, do_sample=True)
print(tok.decode(out[0][inputs.shape[1]:], skip_special_tokens=True))
vLLM
vllm serve LindotAI/Lin-1-Locus --max-model-len 8192
llama.cpp / Ollama (GGUF)
llama-cli -m Lin-1-Locus-Q8_0.gguf -p "Write a Rust function that parses a CSV line into Vec<String>."
Recommended sampling: temperature 0.2 for single answers, 0.8 when sampling several candidates and testing them.
Training
- Supervised fine-tuning of Qwen3.5-4B on Rust instruction data and the model's own test-verified answers (rejection sampling).
- Supervised fine-tuning on curated Rust from permissively licensed sources: files from The Stack Edu (Rust subset) that compile and pass their own unit tests, and compile-checked samples from Strandset-Rust.
All training data was decontaminated against the evaluation sets (12-gram overlap filter).
Limitations
- Focused on Rust; other languages work but are not the target.
- 4B parameters: complex multi-file projects and long-horizon agentic tasks remain hard.
- Always compile and test generated code.
License
Apache 2.0, same as the base model.
- Downloads last month
- 120


Install (macOS, Linux)
# Start a local OpenAI-compatible server with a web UI: llama serve -hf LindotAI/Lin-1-Locus:Q8_0# Run inference directly in the terminal: llama cli -hf LindotAI/Lin-1-Locus:Q8_0