Qwen3.6-27B MTP
See Qwen3.6-27B with MTP in action: demonstration videos
This draft model contains the extracted Multi-Token Prediction (MTP) layers from Qwen/Qwen3.6-27B for use alongside the Qwen3.6-27B-MLX model as a speculative decoder for improved performance.
Tested on a M3 Ultra 512GB RAM using Inferencer app v1.11.5
| Without decoder | ~17.1 tokens/s ~28.36 GiB (debug build) |
| With decoder | ~30.08 tokens/s ~28.99 GiB (debug build) |
Q4.5-bit quant typically achieves higher throughput at no loss in quality with less RAM usage in our coding test
Disclaimer
We are not the creator, originator, or owner of any model listed. Each model is created and provided by third parties. Models may not always be accurate or contextually appropriate. You are responsible for verifying the information before making important decisions. We are not liable for any damages, losses, or issues arising from its use, including data loss or inaccuracies in AI-generated content.
- Downloads last month
- 765
Quantized
Model tree for inferencerlabs/Qwen3.6-27B-MTP-MLX-4.5bit
Base model
Qwen/Qwen3.6-27B
# 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("inferencerlabs/Qwen3.6-27B-MTP-MLX-4.5bit") config = load_config("inferencerlabs/Qwen3.6-27B-MTP-MLX-4.5bit") # 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)