Instructions to use mlx-community/Step-3.5-Flash-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mlx-community/Step-3.5-Flash-4bit 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("mlx-community/Step-3.5-Flash-4bit")

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
LM Studio

Pi new

How to use mlx-community/Step-3.5-Flash-4bit with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "mlx-community/Step-3.5-Flash-4bit"

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": "mlx-community/Step-3.5-Flash-4bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use mlx-community/Step-3.5-Flash-4bit 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 "mlx-community/Step-3.5-Flash-4bit"

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 mlx-community/Step-3.5-Flash-4bit

Run Hermes

hermes

MLX LM

How to use mlx-community/Step-3.5-Flash-4bit with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "mlx-community/Step-3.5-Flash-4bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "mlx-community/Step-3.5-Flash-4bit"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "mlx-community/Step-3.5-Flash-4bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Minimum RAM required to run this model

by Arete7 - opened Feb 5

Discussion

Arete7

Feb 5

What is the minimum RAM required to run this model?

x-polyglot-x

Feb 7

What is the minimum RAM required to run this model?

I am curious on this as well. Wondering if it will run on 128gb Mac Studio

kernelpool

MLX Community org Feb 7

Here's the peak memory you can expect at different context lengths

Context	Prompt TPS	Gen TPS	Peak Memory
1k	423.3	52.0	111.9 GB
2k	586.7	50.2	112.5 GB
4k	622.8	47.9	112.9 GB
8k	596.4	45.3	113.5 GB
16k	506.1	39.0	114.9 GB
32k	374.0	31.8	117.7 GB
64k	239.5	23.0	123.9 GB
128k	133.8	15.7	136.0 GB

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment