Instructions to use rao-studios/Qwen2.5-Coder-7B-Instruct-mlx-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rao-studios/Qwen2.5-Coder-7B-Instruct-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("rao-studios/Qwen2.5-Coder-7B-Instruct-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 rao-studios/Qwen2.5-Coder-7B-Instruct-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 "rao-studios/Qwen2.5-Coder-7B-Instruct-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": "rao-studios/Qwen2.5-Coder-7B-Instruct-mlx-4bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use rao-studios/Qwen2.5-Coder-7B-Instruct-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 "rao-studios/Qwen2.5-Coder-7B-Instruct-mlx-4bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "rao-studios/Qwen2.5-Coder-7B-Instruct-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": "rao-studios/Qwen2.5-Coder-7B-Instruct-mlx-4bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use rao-studios/Qwen2.5-Coder-7B-Instruct-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 "rao-studios/Qwen2.5-Coder-7B-Instruct-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 rao-studios/Qwen2.5-Coder-7B-Instruct-mlx-4bit

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use rao-studios/Qwen2.5-Coder-7B-Instruct-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 "rao-studios/Qwen2.5-Coder-7B-Instruct-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 "rao-studios/Qwen2.5-Coder-7B-Instruct-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"

rao-studios/Qwen2.5-Coder-7B-Instruct-mlx-4bit

Rao Studios' mirror of mlx-community/Qwen2.5-Coder-7B-Instruct-4bit at commit 019cc73c45c770444708a6dd8690c66243cc5c80. The weights, tokenizer, chat template and configuration are byte-for-byte that repository's; nothing was re-quantized or edited. This card and LICENSE (the Apache License 2.0, verbatim from Qwen/Qwen2.5-Coder-7B-Instruct at c03e6d358207e414f1eca0bb1891e29f1db0e242) were added.

It exists so every install of Craft fetches the same bytes from a repository Rao controls: Craft's onboarding recommends it by this Mac's memory, and pins this repository at one commit.

Lineage

Qwen/Qwen2.5-Coder-7B-Instruct, by the Qwen team (Apache-2.0).
mlx-community/Qwen2.5-Coder-7B-Instruct-4bit: that model converted to MLX at 4 bits — the files here.

Shape (from `config.json`)


Architecture	`qwen2`, 28 layers
Quantization	4-bit, group size 64
Weights	4.3 GB of safetensors, 735 tensors
Context	32,768 tokens
Tools	Hermes JSON: the chat template lists every tool's JSON schema inside `<tools>`, and the model answers with one JSON object per call inside `<tool_call>` tags

A call, as the model writes it:

<tool_call>
{"name": "edit_file", "arguments": {"path": "Sources/App/main.swift", "old_string": "print(\"hi\")", "new_string": "print(\"hello\")"}}
</tool_call>

Safety pass

Run by Craft's scripts/mirror-model.py on 2026-10-26, before upload:

Every file is one an MLX model needs; no pickle format and no native code was in the source.
Every weight file is safetensors, its header read by hand: known dtypes, tensors that tile the file exactly, the same tensor names as the index.
Every file matches the SHA-256 the Hub recorded for it at 019cc73c45c770444708a6dd8690c66243cc5c80.
No auto_map (remote code) in the config or the tokenizer config; a chat template is present.

File	Bytes	SHA-256
`added_tokens.json`	605	`58b54bbe36fc752f79a24a271ef66a0a0830054b4dfad94bde757d851968060b`
`config.json`	787	`08762352ba9fded858f24bdd7b8d2fe61aabe7bce1dfdb663db242d574c3e678`
`merges.txt`	1,671,853	`8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5`
`model.safetensors`	4,284,346,255	`56a3d94706833f753e6c6b47ea57af8ef638cd8cc1d74eca1142ba640b26060e`
`model.safetensors.index.json`	51,711	`23cd562592dd96686d2e799eb02e4b578a4038b6045eaefe860d270cc060e24f`
`special_tokens_map.json`	613	`76862e765266b85aa9459767e33cbaf13970f327a0e88d1c65846c2ddd3a1ecd`
`tokenizer.json`	7,031,673	`a8506e7111b80c6d8635951a02eab0f4e1a8e4e5772da83846579e97b16f61bf`
`tokenizer_config.json`	7,308	`f7c61e32b7a17d19bf8e7037dcb74079a833e53ea9801f24008cac68458f03b7`
`vocab.json`	2,776,833	`ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910`

Use with mlx

pip install mlx-lm
mlx_lm.generate --model rao-studios/Qwen2.5-Coder-7B-Instruct-mlx-4bit --prompt "Write a binary search in Swift."

Downloads last month: 243

Safetensors

Model size

8B params

Tensor type

U32

F16

MLX

Hardware compatibility

Quantized

Model tree for rao-studios/Qwen2.5-Coder-7B-Instruct-mlx-4bit

Base model

Qwen/Qwen2.5-7B

Finetuned

Qwen/Qwen2.5-Coder-7B

Finetuned

mlx-community/Qwen2.5-Coder-7B-Instruct-4bit

Finetuned

(2)

this model

rao-studios/Qwen2.5-Coder-7B-Instruct-mlx-4bit

Lineage

Shape (from config.json)

Safety pass

Use with mlx

Model tree for rao-studios/Qwen2.5-Coder-7B-Instruct-mlx-4bit

Shape (from `config.json`)