Instructions to use mlx-community/IQuest-Coder-V1-40B-Instruct-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use mlx-community/IQuest-Coder-V1-40B-Instruct-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/IQuest-Coder-V1-40B-Instruct-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
- Pi
How to use mlx-community/IQuest-Coder-V1-40B-Instruct-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/IQuest-Coder-V1-40B-Instruct-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/IQuest-Coder-V1-40B-Instruct-4bit" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent new
How to use mlx-community/IQuest-Coder-V1-40B-Instruct-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/IQuest-Coder-V1-40B-Instruct-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/IQuest-Coder-V1-40B-Instruct-4bit
Run Hermes
hermes
- OpenClaw new
How to use mlx-community/IQuest-Coder-V1-40B-Instruct-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 "mlx-community/IQuest-Coder-V1-40B-Instruct-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 "mlx-community/IQuest-Coder-V1-40B-Instruct-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"
- MLX LM
How to use mlx-community/IQuest-Coder-V1-40B-Instruct-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/IQuest-Coder-V1-40B-Instruct-4bit"
Run an OpenAI-compatible server
# Install MLX LM uv tool install mlx-lm # Start the server mlx_lm.server --model "mlx-community/IQuest-Coder-V1-40B-Instruct-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/IQuest-Coder-V1-40B-Instruct-4bit", "messages": [ {"role": "user", "content": "Hello"} ] }'
Not working on my Macbook.
Code snippet:
python
from mlx_lm import load, generate
model, tokenizer = load("mlx-community/IQuest-Coder-V1-40B-Instruct-4bit")
Issue Description: The model downloads successfully (21.4GB), but mlx_lm fails to load it because the model architecture type "iquestcoder" is not recognized. The library is looking for a module at mlx_lm.models.iquestcoder which doesn't exist.
Environment:
Python 3.12
pip show mlx-lm
Name: mlx-lm
Version: 0.30.0
Summary: LLMs with MLX and the Hugging Face Hub
Home-page: https://github.com/ml-explore/mlx-lm
Author: MLX Contributors
Author-email: mlx@group.apple.com
License: MIT
Location: /opt/homebrew/Caskroom/miniforge/base/lib/python3.12/site-packages
Requires: jinja2, mlx, numpy, protobuf, pyyaml, sentencepiece, transformers
Required-by:
Model: mlx-community/IQuest-Coder-V1-40B-Instruct-4bit
Question: Is this model architecture supported by the current version of mlx_lm? Do I need to upgrade the library or use a different approach to load this model?
Loading IQuest-Coder-V1-40B-Instruct-4bit model...
This may take a few minutes on first run as it downloads the model.
Fetching 17 files: 100%|βββββββββββββββββββββββ| 17/17 [08:47<00:00, 31.06s/it]
Download complete: 100%|ββββββββββββββββββββ| 21.4G/21.4G [08:48<00:00, 40.5MB/s]
ERROR:root:Model type iquestcoder not supported.
Traceback (most recent call last):
File "/path/to/site-packages/mlx_lm/utils.py", line 71, in _get_classes
arch = importlib.import_module(f"mlx_lm.models.{model_type}")
File "/path/to/importlib/init.py", line 90, in import_module
return _bootstrap._gcd_import(name[level:], package, level)
ModuleNotFoundError: No module named 'mlx_lm.models.iquestcoder'
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "run_iquest_coder.py", line 7, in
model, tokenizer = load("mlx-community/IQuest-Coder-V1-40B-Instruct-4bit")
File "/path/to/site-packages/mlx_lm/utils.py", line 322, in load
model, config = load_model(model_path, lazy, model_config=model_config)
File "/path/to/site-packages/mlx_lm/utils.py", line 201, in load_model
model_class, model_args_class = get_model_classes(config=config)
File "/path/to/site-packages/mlx_lm/utils.py", line 75, in _get_classes
raise ValueError(msg)
ValueError: Model type iquestcoder not supported.
Support has been merged, but you need to install from source until there's an official release: https://github.com/ml-explore/mlx-lm
Support for this model was added in MLX-LM 0.30.1