Image-Text-to-Text
MLX
Safetensors
qwen3_5
mtplx
qwen3.6
speculative-decoding
multi-token-prediction
conversational
4-bit precision
Instructions to use Youssofal/Qwen3.6-27B-MTPLX-Optimized-Quality with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use Youssofal/Qwen3.6-27B-MTPLX-Optimized-Quality 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("Youssofal/Qwen3.6-27B-MTPLX-Optimized-Quality") config = load_config("Youssofal/Qwen3.6-27B-MTPLX-Optimized-Quality") # 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
- LM Studio
- Pi new
How to use Youssofal/Qwen3.6-27B-MTPLX-Optimized-Quality with Pi:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "Youssofal/Qwen3.6-27B-MTPLX-Optimized-Quality"
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": "Youssofal/Qwen3.6-27B-MTPLX-Optimized-Quality" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent new
How to use Youssofal/Qwen3.6-27B-MTPLX-Optimized-Quality 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 "Youssofal/Qwen3.6-27B-MTPLX-Optimized-Quality"
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 Youssofal/Qwen3.6-27B-MTPLX-Optimized-Quality
Run Hermes
hermes
| { | |
| "arch_id": "qwen3-next-mtp", | |
| "artifact_role": "optimized-quality", | |
| "benchmark_summary": { | |
| "acceptance_by_depth": [ | |
| 0.9556737588652481, | |
| 0.852575488454707, | |
| 0.7406749555950266 | |
| ], | |
| "artifact": "/tmp/mtplx-flat8-maxfan-bakeoff-20260510-040405/flat8-int8-flappy2k.json", | |
| "peak_gib": 27.615886019542813, | |
| "suite": "flappy 2k depth3 max-fan", | |
| "tok_s": 33.6276837588148, | |
| "verify_ms_per_call": 88.13897531140259 | |
| }, | |
| "exactness_baseline": { | |
| "gate": "flat8-quality-mtp-bakeoff", | |
| "notes": "Validated with mtplx inspect and local Flappy 2k max-fan bakeoff; 2k Flappy validator truncates before balanced delimiter completion, so code-shape validator is the meaningful capped-run gate.", | |
| "status": "candidate-promoted-by-user-decision" | |
| }, | |
| "mtp_depth_max": 3, | |
| "mtp_sidecar": "CyanKiwi calibrated INT8 affine group128, BF16 aux preserved", | |
| "mtplx_version": "0.1.0-preview", | |
| "recommended_profile": "performance-cold", | |
| "sampler": { | |
| "temperature": 0.6, | |
| "top_k": 20, | |
| "top_p": 0.95 | |
| }, | |
| "target_precision": "flat8 affine group64", | |
| "verified_on": { | |
| "hardware": "M5 Max local max-fan bakeoff", | |
| "model": "Qwen3.6-27B-MTPLX-Optimized-Quality", | |
| "status": "validated-candidate", | |
| "timestamp": "2026-05-10T04:16:00+01:00" | |
| } | |
| } | |