Instructions to use tongrow/MLX-Qwopus3.5-9B-Coder-oQ4-fp16-mtp with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tongrow/MLX-Qwopus3.5-9B-Coder-oQ4-fp16-mtp with MLX:

# Make sure mlx-vlm is installed
# pip install --upgrade mlx-vlm

from mlx_vlm import load, generate
from mlx_vlm.prompt_utils import apply_chat_template
from mlx_vlm.utils import load_config

# Load the model
model, processor = load("tongrow/MLX-Qwopus3.5-9B-Coder-oQ4-fp16-mtp")
config = load_config("tongrow/MLX-Qwopus3.5-9B-Coder-oQ4-fp16-mtp")

# Prepare input
image = ["http://images.cocodataset.org/val2017/000000039769.jpg"]
prompt = "Describe this image."

# Apply chat template
formatted_prompt = apply_chat_template(
    processor, config, prompt, num_images=1
)

# Generate output
output = generate(model, processor, formatted_prompt, image)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use tongrow/MLX-Qwopus3.5-9B-Coder-oQ4-fp16-mtp with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "tongrow/MLX-Qwopus3.5-9B-Coder-oQ4-fp16-mtp"

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": "tongrow/MLX-Qwopus3.5-9B-Coder-oQ4-fp16-mtp"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent

How to use tongrow/MLX-Qwopus3.5-9B-Coder-oQ4-fp16-mtp 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 "tongrow/MLX-Qwopus3.5-9B-Coder-oQ4-fp16-mtp"

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 tongrow/MLX-Qwopus3.5-9B-Coder-oQ4-fp16-mtp

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use tongrow/MLX-Qwopus3.5-9B-Coder-oQ4-fp16-mtp with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "tongrow/MLX-Qwopus3.5-9B-Coder-oQ4-fp16-mtp"

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 "tongrow/MLX-Qwopus3.5-9B-Coder-oQ4-fp16-mtp" \
  --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-Qwopus3.5-9B-Coder-oQ4-fp16-mtp

oQ4 quantized MLX release of Qwopus3.5-9B-Coder optimized for Apple Silicon inference with Native MTP preserved.

Built with oMLX v0.3.9.dev2.

Quantization Details

Quantization method:

Non-quantized weight dtype:

float16

Enabled options:

Preserve MTP weights

This preserves:

mtp.* tensors
required config fields

allowing Native MTP to remain functional after quantization.

The resulting model includes the -mtp suffix accordingly.

Why float16?

float16 was selected instead of bfloat16 because Apple M1/M2 chips execute native fp16 especially efficiently during prefill workloads.

On Apple Silicon:

fp16 generally provides faster prompt ingestion
bf16 may offer slightly better numerical stability
M3/M4 systems may benefit more from bf16

For this release, the priority was maximum real-world inference responsiveness on M1/M2 hardware.

Tested Hardware

Device:

MacBook Pro M1
16GB unified memory

Runtime configuration:

Native MTP: enabled
Context window: 65536
Temperature: 1

Integrated into:

Hermes agent workflow

Observed performance:

Prompt processing (excluding cached): ~219.3 tok/s
Token generation: ~25.1 tok/s

Format

Format:

MLX safetensors

Designed specifically for:

Apple Silicon
MLX runtimes
Native MTP workflows

Compatibility

Tested with:

oMLX
LM Studio

Base Model

Base model by Jackrong:

Qwopus3.5-9B-Coder

All credit for the original architecture and training belongs to the upstream creators.

Notes

This release focuses on:

Apple Silicon efficiency
preserving Native MTP support
practical local coding-agent workflows
high context operation within 16GB unified memory constraints

Downloads last month: 268

Safetensors

Model size

10B params

Tensor type

U32

F16

MLX

Hardware compatibility

4-bit

Model tree for tongrow/MLX-Qwopus3.5-9B-Coder-oQ4-fp16-mtp

Base model

Qwen/Qwen3.5-9B-Base

Finetuned

Qwen/Qwen3.5-9B

Finetuned

unsloth/Qwen3.5-9B

Finetuned

Jackrong/Qwopus3.5-9B-v3.5

Adapter

Jackrong/Qwopus3.5-9B-Coder

Quantized

(8)

this model