Instructions to use RecursiveSI/flint-int4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RecursiveSI/flint-int4 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("RecursiveSI/flint-int4")

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 RecursiveSI/flint-int4 with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "RecursiveSI/flint-int4"

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "RecursiveSI/flint-int4"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use RecursiveSI/flint-int4 with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "RecursiveSI/flint-int4"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "RecursiveSI/flint-int4"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "RecursiveSI/flint-int4",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use RecursiveSI/flint-int4 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 "RecursiveSI/flint-int4"

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 RecursiveSI/flint-int4

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use RecursiveSI/flint-int4 with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "RecursiveSI/flint-int4"

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 "RecursiveSI/flint-int4" \
  --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"

flint-int4 / README.md

alexey-recursive

Trim release files and fix model-card links and training disclosure

3b93f90 verified 1 day ago

preview code

Raw History Blame Contribute Delete

1.62 kB

metadata

license: apache-2.0
pipeline_tag: text-generation
tags:
  - mlx
  - int4
  - safetensors

Flint INT4

MLX-format INT4 weights for Recursive Flint, primarily intended for local inference on Apple Silicon. Projections and experts use group-64 affine INT4; embeddings use INT8. The weights occupy approximately 22.6 GB.

See Flint’s model card for model details, benchmarks, chat conventions, and limitations.

Use with Rec

Follow Rec’s requirements and installation guide, then launch pi or OpenCode:

rec launch pi
# Or use OpenCode:
rec launch opencode

Download the weights separately

With the Hugging Face CLI installed:

hf download RecursiveSI/flint-int4 --local-dir flint-int4

For llama.cpp on Metal, use Flint INT4 GGUF.

Training data

Flint’s training data included publicly available and crawled web documents, text and code, commercially licensed data, and AI-generated synthetic data. Post-training included instruction tuning, reinforcement learning and human-preference data. See the base Flint model card for shared model and training information.

License

Apache License 2.0.