Instructions to use divinetribe/AesCode-8B-MLX-bf16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use divinetribe/AesCode-8B-MLX-bf16 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("divinetribe/AesCode-8B-MLX-bf16")
config = load_config("divinetribe/AesCode-8B-MLX-bf16")

# 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 divinetribe/AesCode-8B-MLX-bf16 with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "divinetribe/AesCode-8B-MLX-bf16"

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": "divinetribe/AesCode-8B-MLX-bf16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent

How to use divinetribe/AesCode-8B-MLX-bf16 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 "divinetribe/AesCode-8B-MLX-bf16"

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 divinetribe/AesCode-8B-MLX-bf16

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use divinetribe/AesCode-8B-MLX-bf16 with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "divinetribe/AesCode-8B-MLX-bf16"

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 "divinetribe/AesCode-8B-MLX-bf16" \
  --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"

divinetribe commited on 6 days ago

Commit

3735aab

verified ·

1 Parent(s): ba13e5b

Cross-link other quant sizes

Browse files

Files changed (1) hide show

README.md +5 -0

README.md CHANGED Viewed

@@ -22,6 +22,10 @@ kept intact** so it reads a design or screenshot and writes the HTML/CSS back on
 Silicon. No quantization: every weight is the original bf16. **750 tensors**, 17.5 GB, four
 shards.
 AesCode generates information-rich visual artifacts (slides, posters, dashboards, reports)
 as structured, editable, verifiable HTML/CSS. It starts from
 [Qwen3-VL-8B-Instruct](https://huggingface.co/Qwen/Qwen3-VL-8B-Instruct) and is trained with
@@ -36,6 +40,7 @@ rewards.
 - **Architecture:** `Qwen3VLForConditionalGeneration` — a `qwen3_vl` vision tower feeding the
   `qwen3_vl_text` decoder. 8.8B parameters.
 - **This repo:** bf16 MLX weights, vision kept, for [`mlx-vlm`](https://github.com/Blaizzy/mlx-vlm).
 ## Running it (MLX)

 Silicon. No quantization: every weight is the original bf16. **750 tensors**, 17.5 GB, four
 shards.
+**This is the full-quality build. Smaller sizes that passed the same vision check:
+[8-bit (about half the size, for 16 GB machines)](https://huggingface.co/divinetribe/AesCode-8B-MLX-8bit)
+· [4-bit (smallest, for 8 GB machines)](https://huggingface.co/divinetribe/AesCode-8B-MLX-4bit).**
 AesCode generates information-rich visual artifacts (slides, posters, dashboards, reports)
 as structured, editable, verifiable HTML/CSS. It starts from
 [Qwen3-VL-8B-Instruct](https://huggingface.co/Qwen/Qwen3-VL-8B-Instruct) and is trained with
 - **Architecture:** `Qwen3VLForConditionalGeneration` — a `qwen3_vl` vision tower feeding the
   `qwen3_vl_text` decoder. 8.8B parameters.
 - **This repo:** bf16 MLX weights, vision kept, for [`mlx-vlm`](https://github.com/Blaizzy/mlx-vlm).
+- **Other sizes:** [8-bit](https://huggingface.co/divinetribe/AesCode-8B-MLX-8bit) · [4-bit](https://huggingface.co/divinetribe/AesCode-8B-MLX-4bit).
 ## Running it (MLX)