Instructions to use henrybravo/Qwen3.5-35B-A3B-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use henrybravo/Qwen3.5-35B-A3B-4bit 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("henrybravo/Qwen3.5-35B-A3B-4bit")
config = load_config("henrybravo/Qwen3.5-35B-A3B-4bit")

# 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 henrybravo/Qwen3.5-35B-A3B-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 "henrybravo/Qwen3.5-35B-A3B-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": "henrybravo/Qwen3.5-35B-A3B-4bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent

How to use henrybravo/Qwen3.5-35B-A3B-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 "henrybravo/Qwen3.5-35B-A3B-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 henrybravo/Qwen3.5-35B-A3B-4bit

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use henrybravo/Qwen3.5-35B-A3B-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 "henrybravo/Qwen3.5-35B-A3B-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 "henrybravo/Qwen3.5-35B-A3B-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"

Qwen3.5-35B-A3B-4bit (MLX)

This repository provides an MLX quantized conversion of Qwen/Qwen3.5-35B-A3B, prepared for local inference on Apple Silicon.

This is an unofficial conversion published by henrybravo. All model capabilities, limitations, and licensing inherit from the original Qwen release.

Model summary

Base model: Qwen/Qwen3.5-35B-A3B
Architecture: Qwen3_5MoeForConditionalGeneration (qwen3_5_moe)
Quantization: affine, group size 64, primary weights at 4-bit
Note: MoE gate tensors are kept at 8-bit (as reflected in config.json)
Weight format: safetensors (4 shards)
Intended runtime: mlx-vlm / MLX ecosystem on macOS

Why this variant

This 4-bit build is tuned for practical local responsiveness while keeping strong quality for interactive use.

Typical local memory target used in router config: about 20 GB
Local default tested in this setup: max_tokens = 16384

Install

pip install -U mlx==0.31.0 mlx-lm==0.31.0 mlx-vlm==0.4.0 transformers==5.3.0

For OpenAI-compatible local serving and routing on top of MLX models, see mlx-router.

Quick usage (mlx-vlm)

You can run the examples below directly with mlx_vlm.generate, or serve the model through mlx-router.

Text prompt

python -m mlx_vlm.generate \
  --model /path/to/Qwen3.5-35B-A3B-4bit \
  --max-tokens 100 \
  --temperature 0.0 \
  --prompt "Hello, what model are you?"

Vision prompt

python -m mlx_vlm.generate \
  --model /path/to/Qwen3.5-35B-A3B-4bit \
  --max-tokens 200 \
  --temperature 0.0 \
  --prompt "Describe this image in detail." \
  --image https://upload.wikimedia.org/wikipedia/commons/thumb/a/a7/Camponotus_flavomarginatus_ant.jpg/320px-Camponotus_flavomarginatus_ant.jpg

Conversion command used

mlx_vlm.convert \
  --hf-path Qwen/Qwen3.5-35B-A3B \
  --mlx-path ~/models/models--henrybravo--Qwen3.5-35B-A3B-4bit \
  -q \
  --q-bits 4 \
  --dtype bfloat16

Notes

This repository stores MLX-converted weights; it is not a standard Transformers checkpoint.
For best official guidance, benchmarks, and serving docs, see the upstream Qwen model card.

Upstream references

Base model: https://huggingface.co/Qwen/Qwen3.5-35B-A3B
Original license file: https://huggingface.co/Qwen/Qwen3.5-35B-A3B/blob/main/LICENSE
Qwen blog: https://qwen.ai/blog?id=qwen3.5

Downloads last month: 24

Safetensors

Model size

35B params

Tensor type

U32

BF16

F32

MLX

Hardware compatibility

4-bit

Model tree for henrybravo/Qwen3.5-35B-A3B-4bit

Base model

Qwen/Qwen3.5-35B-A3B-Base

Finetuned

Qwen/Qwen3.5-35B-A3B

Quantized

(301)

this model