Instructions to use AutomatosX/AX-Qwen3.6-35B-A3B-MLX-6bit-MTP with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AutomatosX/AX-Qwen3.6-35B-A3B-MLX-6bit-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("AutomatosX/AX-Qwen3.6-35B-A3B-MLX-6bit-MTP")
config = load_config("AutomatosX/AX-Qwen3.6-35B-A3B-MLX-6bit-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 AutomatosX/AX-Qwen3.6-35B-A3B-MLX-6bit-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 "AutomatosX/AX-Qwen3.6-35B-A3B-MLX-6bit-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": "AutomatosX/AX-Qwen3.6-35B-A3B-MLX-6bit-MTP"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent

How to use AutomatosX/AX-Qwen3.6-35B-A3B-MLX-6bit-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 "AutomatosX/AX-Qwen3.6-35B-A3B-MLX-6bit-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 AutomatosX/AX-Qwen3.6-35B-A3B-MLX-6bit-MTP

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use AutomatosX/AX-Qwen3.6-35B-A3B-MLX-6bit-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 "AutomatosX/AX-Qwen3.6-35B-A3B-MLX-6bit-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 "AutomatosX/AX-Qwen3.6-35B-A3B-MLX-6bit-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"

AutomatosX commited on Jul 21

Commit

bf94eb9

verified ·

1 Parent(s): 64de9c1

Add top-level ax_provenance.json for Qwen MTP package identity

Browse files

Files changed (1) hide show

ax_provenance.json +53 -0

ax_provenance.json ADDED Viewed

	@@ -0,0 +1,53 @@

+{
+  "schema_version": "ax.qwen_mtp_package_provenance.v1",
+  "published_by": "AutomatosX",
+  "repository": "AutomatosX/AX-Qwen3.6-35B-A3B-MLX-6bit-MTP",
+  "release_type": "ax-mtp-package",
+  "logical_parameters": 35107181936,
+  "task": "image-text-to-text",
+  "format": "mlx",
+  "quantization": "6-bit",
+  "target": {
+    "repo_id": "mlx-community/Qwen3.6-35B-A3B-6bit",
+    "revision": "cb7e092ef8efe540bc3672c8929c4adbe5f4f759",
+    "weight_shards_byte_exact": true,
+    "notes": "Target MLX weight shards are transparent to the pinned mlx-community revision; AutomatosX adds MTP packaging."
+  },
+  "mtp": {
+    "enabled": true,
+    "manifest_path": "ax_mtp_sidecar_manifest.json",
+    "manifest_schema": "ax.mtp_sidecar_provenance.v1",
+    "source_repo_id": "Qwen/Qwen3.6-35B-A3B",
+    "source_revision": null,
+    "backend": "qwen-moe-packed",
+    "max_depth": 1,
+    "tensor_count": 20,
+    "sidecar": {
+      "path": "mtp.safetensors",
+      "exists": true,
+      "size_bytes": 1689283731,
+      "sha256": "7bab930aa78a9be90c8a433c09894428bd115424a2be928eb718fd3904e61942"
+    },
+    "runtime_file": {
+      "path": "mtplx_runtime.json",
+      "exists": true,
+      "size_bytes": 669,
+      "sha256": "6fd307184c888de5f88f9ea2fe1a7b61aa106c30642de1f9bc85dbff68a1e3e1"
+    },
+    "transform": {
+      "norm_policy": "shift_mtp_norm_weights_by_1",
+      "moe_expert_unpack": true,
+      "quantize_bits": null,
+      "quantize_group_size": null
+    }
+  },
+  "package": {
+    "includes_ax_native_manifest": true,
+    "includes_mtp_sidecar_manifest": true,
+    "top_level_provenance_added": true
+  },
+  "related_manifests": {
+    "ax_mtp_sidecar_manifest": "ax_mtp_sidecar_manifest.json",
+    "model_manifest": "model-manifest.json"
+  }
+}