Instructions to use interimlabs/InterimLabs-Qwen3.5-4B-MLX-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use interimlabs/InterimLabs-Qwen3.5-4B-MLX-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("interimlabs/InterimLabs-Qwen3.5-4B-MLX-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 Settings
LM Studio

How to use interimlabs/InterimLabs-Qwen3.5-4B-MLX-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 "interimlabs/InterimLabs-Qwen3.5-4B-MLX-4bit"

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": "interimlabs/InterimLabs-Qwen3.5-4B-MLX-4bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use interimlabs/InterimLabs-Qwen3.5-4B-MLX-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 "interimlabs/InterimLabs-Qwen3.5-4B-MLX-4bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "interimlabs/InterimLabs-Qwen3.5-4B-MLX-4bit"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "interimlabs/InterimLabs-Qwen3.5-4B-MLX-4bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use interimlabs/InterimLabs-Qwen3.5-4B-MLX-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 "interimlabs/InterimLabs-Qwen3.5-4B-MLX-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 interimlabs/InterimLabs-Qwen3.5-4B-MLX-4bit

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use interimlabs/InterimLabs-Qwen3.5-4B-MLX-4bit with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "interimlabs/InterimLabs-Qwen3.5-4B-MLX-4bit"

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 "interimlabs/InterimLabs-Qwen3.5-4B-MLX-4bit" \
  --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"

Interim Labs Qwen3.5-4B · MLX 4-bit

A standalone text-only MLX 4-bit release published by Interim Labs for local text generation on Apple Silicon. This package derives from Qwen/Qwen3.5-4B. Interim Labs packages and documents this derivative; the upstream model and conversion sources are credited below.

Model series

Part of the Interim Labs Qwen3.5 series: three sizes, each with an original Qwen3.5 variant and a Huihui abliterated variant, in two formats.

Model	MLX 4-bit	GGUF Q4_K_M
Qwen3.5 2B	MLX	GGUF
Huihui Qwen3.5 2B abliterated	MLX	GGUF
Qwen3.5 4B	MLX	GGUF
Huihui Qwen3.5 4B abliterated	MLX	GGUF
Qwen3.5 9B	MLX	GGUF
Huihui Qwen3.5 9B abliterated	MLX	GGUF

Package details

Property	Value
Parameter class	4B
Format	MLX / Safetensors
Quantization	4-bit affine, group size 64
Weight file	`model.safetensors`
Weight size	2.37 GB (2,367,224,773 bytes)
Model type	`qwen3_5_text`
Configured context	8,192 tokens
Retained text tensors	924

This package contains language-model tensors only and does not provide image input. Text-only derivation removed 297 vision tensors. The packaged configuration sets the context to 8,192 tokens; this is not the upstream model’s full advertised context length.

Usage and runtime requirements

Download the package with the Hugging Face CLI:

hf download interimlabs/InterimLabs-Qwen3.5-4B-MLX-4bit

Use an MLX runtime on Apple Silicon that supports the qwen3_5_text architecture and this package’s quantization. Use the included tokenizer and chat template, and keep the total context within 8,192 tokens. Generic Python mlx_lm builds without qwen3_5_text support may fail to load this package. Runtime compatibility across applications has not been comprehensively verified.

Sources and conversion

MLX source: mlx-community/Qwen3.5-4B-4bit at 0e7ffd5c629ef7719d4cbc04069232580bfa9d9c.
Reference upstream: Qwen/Qwen3.5-4B at 851bf6e806efd8d0a36b00ddf55e13ccb7b8cd0a.

The conversion source does not establish the exact upstream revision used for its conversion. The reference revision above documents the inspected upstream snapshot, not a verified conversion lineage.

See provenance.json for source and package metadata.

Weight-file SHA-256:

799b8fe437040924178c0ce28acb4fb0a5830a4a6f0ddcff004e13ab468bfbf8

Evaluation and limitations

This release does not include a comprehensive benchmark of the packaged model. No writing-quality, reliability, or performance improvement over the credited source is claimed.

License and credits

Distributed under Apache-2.0. Credit belongs to the Qwen team and the conversion authors linked above. Interim Labs publishes this package and its documentation. See the linked upstream cards for the original model details and limitations.