Instructions to use EigenLabs/Qwen3.5-35B-A3B-MLX-VL-4bit-g64 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use EigenLabs/Qwen3.5-35B-A3B-MLX-VL-4bit-g64 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("EigenLabs/Qwen3.5-35B-A3B-MLX-VL-4bit-g64")
config = load_config("EigenLabs/Qwen3.5-35B-A3B-MLX-VL-4bit-g64")

# 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 EigenLabs/Qwen3.5-35B-A3B-MLX-VL-4bit-g64 with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "EigenLabs/Qwen3.5-35B-A3B-MLX-VL-4bit-g64"

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": "EigenLabs/Qwen3.5-35B-A3B-MLX-VL-4bit-g64"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent

How to use EigenLabs/Qwen3.5-35B-A3B-MLX-VL-4bit-g64 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 "EigenLabs/Qwen3.5-35B-A3B-MLX-VL-4bit-g64"

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 EigenLabs/Qwen3.5-35B-A3B-MLX-VL-4bit-g64

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use EigenLabs/Qwen3.5-35B-A3B-MLX-VL-4bit-g64 with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "EigenLabs/Qwen3.5-35B-A3B-MLX-VL-4bit-g64"

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 "EigenLabs/Qwen3.5-35B-A3B-MLX-VL-4bit-g64" \
  --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-MLX-VL-4bit-g64 / verification.json

gajesh

Publish all-affine-W4 MLX VLM with inline W4 MTP

8964653 verified 18 days ago

Raw

History Blame Contribute Delete

1.67 kB

	{
	"schema_version": 1,
	"artifact": "EigenLabs/Qwen3.5-35B-A3B-MLX-VL-4bit-g64",
	"checks": {
	"source_cache_verification": {
	"status": "pass",
	"checked_files": 27
	},
	"safetensors_index_exact_coverage": {
	"status": "pass",
	"indexed_tensors": 2136,
	"shards": 5
	},
	"all_quantized_modules_are_affine_w4_g64": {
	"status": "pass",
	"quantized_modules": 525,
	"eight_bit_modules": 0
	},
	"inline_mtp_structure": {
	"status": "pass",
	"source_tensors": 785,
	"serialized_tensors": 46,
	"source_parameters": 844640768
	},
	"inline_mtp_affine_spot_checks": {
	"status": "pass",
	"fc_4bit_mean_abs_error": 0.0005984869785606861,
	"q_proj_4bit_mean_abs_error": 0.0014587895711883903,
	"expert0_gate_4bit_mean_abs_error": 0.0012867144541814923,
	"router_4bit_mean_abs_error": 0.0008649227092973888,
	"shifted_norm_max_abs_error": 0.0
	},
	"chat_template_source_parity": {
	"status": "pass",
	"sha256": "a4aee8afcf2e0711942cf848899be66016f8d14a889ff9ede07bca099c28f715"
	},
	"target_only_benchmark": {
	"status": "pass",
	"mlx_vlm_version": "0.6.15",
	"prompt_tokens": 1701,
	"generation_tokens": 128,
	"measured_iterations": 3,
	"median_prefill_tokens_per_second": 1642.0583817114323,
	"median_decode_tokens_per_second": 113.67484303705231,
	"peak_memory_gb": 23.252961806,
	"mtp_active": false
	},
	"image_inference": {
	"status": "not_run"
	},
	"mtp_speculative_parity": {
	"status": "not_run"
	},
	"video_inference": {
	"status": "not_run"
	}
	}
	}