Instructions to use pgmharikrishnan/Flint-MLX-Serve-mixed-4-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pgmharikrishnan/Flint-MLX-Serve-mixed-4-8bit 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("pgmharikrishnan/Flint-MLX-Serve-mixed-4-8bit")

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 pgmharikrishnan/Flint-MLX-Serve-mixed-4-8bit with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "pgmharikrishnan/Flint-MLX-Serve-mixed-4-8bit"

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": "pgmharikrishnan/Flint-MLX-Serve-mixed-4-8bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use pgmharikrishnan/Flint-MLX-Serve-mixed-4-8bit with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "pgmharikrishnan/Flint-MLX-Serve-mixed-4-8bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "pgmharikrishnan/Flint-MLX-Serve-mixed-4-8bit"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "pgmharikrishnan/Flint-MLX-Serve-mixed-4-8bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use pgmharikrishnan/Flint-MLX-Serve-mixed-4-8bit 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 "pgmharikrishnan/Flint-MLX-Serve-mixed-4-8bit"

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 pgmharikrishnan/Flint-MLX-Serve-mixed-4-8bit

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use pgmharikrishnan/Flint-MLX-Serve-mixed-4-8bit with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "pgmharikrishnan/Flint-MLX-Serve-mixed-4-8bit"

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 "pgmharikrishnan/Flint-MLX-Serve-mixed-4-8bit" \
  --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-MLX-Serve-mixed-4-8bit

An Apple-Silicon MLX pack of Recursive Flint, a 39.8B-total / 2.5B-active coding-agent MoE.

Pack size: ~31 GB. Recommended RAM: 40 GB+ unified memory. Requires mlx-serve with Flint support (in progress).

Recipe

Routed expert banks are affine 4-bit at group size 64. Attention, routers, shared-expert weights, embeddings, and LM head are affine 8-bit at group size 64; norms, vectors, and matrices with fewer than 32 rows remain BF16.

The checkpoint was converted shard-by-shard on CPU from RecursiveSI/flint, retaining the upstream Apache-2.0 license.

mlx-serve quickstart

mlx-serve --model pgmharikrishnan/Flint-MLX-Serve-mixed-4-8bit

OpenAI-compatible request:

curl http://127.0.0.1:11234/v1/chat/completions \
  -H 'Content-Type: application/json' \
  -d '{"model":"pgmharikrishnan/Flint-MLX-Serve-mixed-4-8bit","messages":[{"role":"user","content":"Write a Python hello world."}]}'

Results

Teacher-forced fidelity vs BF16 (256 tokens of prose): top-1 agreement 87.1% (pass threshold ≥85%), mean full-vocabulary KL 0.097 nats. ✅ Passes. For comparison, the uniform 4-bit pack scores 61.3% / 0.73 nats, so this mixed pack is the recommended Flint quant.

mlx-serve standard benchmark: pending GPU-locked run.

Downloads last month: 2,719

Safetensors

Model size

40B params

Tensor type

U32

BF16

MLX

Hardware compatibility

8-bit

Model tree for pgmharikrishnan/Flint-MLX-Serve-mixed-4-8bit

Base model

RecursiveSI/flint

Quantized

(96)

this model