Instructions to use MoringLabs/Qwen3.5-122B-A10B-MLX-3.7bit-VL with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MoringLabs/Qwen3.5-122B-A10B-MLX-3.7bit-VL 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("MoringLabs/Qwen3.5-122B-A10B-MLX-3.7bit-VL")
config = load_config("MoringLabs/Qwen3.5-122B-A10B-MLX-3.7bit-VL")

# 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 MoringLabs/Qwen3.5-122B-A10B-MLX-3.7bit-VL with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "MoringLabs/Qwen3.5-122B-A10B-MLX-3.7bit-VL"

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": "MoringLabs/Qwen3.5-122B-A10B-MLX-3.7bit-VL"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use MoringLabs/Qwen3.5-122B-A10B-MLX-3.7bit-VL 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 "MoringLabs/Qwen3.5-122B-A10B-MLX-3.7bit-VL"

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 MoringLabs/Qwen3.5-122B-A10B-MLX-3.7bit-VL

Run Hermes

hermes

OpenClaw new

How to use MoringLabs/Qwen3.5-122B-A10B-MLX-3.7bit-VL with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "MoringLabs/Qwen3.5-122B-A10B-MLX-3.7bit-VL"

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 "MoringLabs/Qwen3.5-122B-A10B-MLX-3.7bit-VL" \
  --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"

Qwen3.5-122B-A10B-MLX-3.7bit-VL / README.md

MoringLabs

Update README.md

a764f22 verified 4 months ago

preview code

Raw

History Blame Contribute Delete

3.32 kB

metadata

license: apache-2.0
language:
  - multilingual
base_model: Qwen/Qwen3.5-122B-A10B
base_model_relation: quantized
tags:
  - mlx
  - quantization
  - mixed-precision
  - vision
  - multimodal
  - qwen3.5
  - moe
  - 122B
  - apple-silicon
library_name: mlx
pipeline_tag: image-text-to-text
model_type: qwen3_5_moe
model_name: Qwen3.5-122B-A10B-MLX-3.7bit-VL
metadata:
  parameters:
    - 122B
extra_gated_heading: Qwen3.5-122B-A10B (MLX 3.7-bit VL)

Qwen3.5-122B-A10B-MLX-3.7bit-VL

Mixed-precision MLX quantization of Qwen3.5-122B-A10B — Alibaba's latest MoE model with full vision support preserved in BF16.

3.655 BPW | 52 GB | Vision preserved (BF16)

🚀 Hardware Optimization

This model brings 122B-class multimodal performance to Apple Silicon. By utilizing advanced mixed-precision quantization, we've compressed the model from uniform 4-bit's 65GB down to 52GB — a 13GB reduction — while preserving the full vision pipeline at BF16 precision for lossless image understanding.

This optimization unlocks two distinct local inference experiences:

64GB Unified Memory (Minimum): The uniform 4-bit quantization weighs 65GB and simply cannot fit in 64GB at all. This quantization breaks that barrier — fitting a full 122B multimodal model into 64GB for the first time, pushing the hardware boundaries to make local 122B vision+language inference possible on edge devices.
96GB+ Unified Memory (Recommended): Delivers an uncompromised, buttery-smooth multimodal experience. The efficient footprint frees up massive headroom for the KV cache, completely unlocking ultimate long-context capabilities for both text and vision tasks.

Quantization

4-tier mixed precision by functional sensitivity:

Bits	Layers	% Params	Description
BF16	—	~2%	Vision tower, norm, router, conv1d — preserving full visual fidelity
6-bit	—	~8%	Embeddings, v/o_proj, edge layers, full_attention q/k
4-bit	—	~3%	DeltaNet attention, shared expert
3-bit	—	~87%	Expert FFN (256 experts, 8 active/token)

Benchmark (M2 Max 96GB)

	This (3.7bit)	Uniform 4bit
Model size	52 GB	65 GB
Peak memory (ctx=4k)	55.1 GB	67.7 GB
Prefill (1k ctx)	219.0 tok/s	210.5 tok/s
Prefill (4k ctx)	230.6 tok/s	227.7 tok/s
Generation (1k ctx)	36.2 tok/s	38.3 tok/s
Generation (4k ctx)	33.6 tok/s	35.8 tok/s

Speed is virtually identical, but the 13GB saved makes the difference between a usable and unusable long-context experience on 96GB machines.

Quality (WikiText-2 Perplexity)

Lower is better. Evaluated on 128 sequences × 2048 tokens.

Metric	Value
Mean Perplexity	5.3536
Median Perplexity	5.3639
Trimmed Mean Perplexity	5.6631

Usage

from mlx_vlm import load, generate

model, processor = load("MoringLabs/Qwen3.5-122B-A10B-MLX-3.7bit-VL")

# 文本对话
response = generate(model, processor, prompt="Hello!", max_tokens=200)

# 图像理解
response = generate(model, processor, prompt="Describe this image", image="photo.jpg", max_tokens=200)
print(response)

License

Apache 2.0