Text Generation
MLX
Safetensors
qwen3_5
apple-silicon
speculative-decoding
qwen
qwen3
qwen3-next
mtp
mtplx
local-ai
conversational
4-bit precision
Instructions to use Youssofal/Qwen3.6-27B-MTPLX-Optimized-Speed 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-Speed with MLX:
# Make sure mlx-lm is installed # pip install --upgrade mlx-lm # Generate text with mlx-lm from mlx_lm import load, generate model, tokenizer = load("Youssofal/Qwen3.6-27B-MTPLX-Optimized-Speed") prompt = "Write a story about Einstein" messages = [{"role": "user", "content": prompt}] prompt = tokenizer.apply_chat_template( messages, add_generation_prompt=True ) text = generate(model, tokenizer, prompt=prompt, verbose=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps
- LM Studio
- Pi new
How to use Youssofal/Qwen3.6-27B-MTPLX-Optimized-Speed 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-Speed"
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-Speed" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent new
How to use Youssofal/Qwen3.6-27B-MTPLX-Optimized-Speed 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-Speed"
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-Speed
Run Hermes
hermes
- MLX LM
How to use Youssofal/Qwen3.6-27B-MTPLX-Optimized-Speed with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Interactive chat REPL mlx_lm.chat --model "Youssofal/Qwen3.6-27B-MTPLX-Optimized-Speed"
Run an OpenAI-compatible server
# Install MLX LM uv tool install mlx-lm # Start the server mlx_lm.server --model "Youssofal/Qwen3.6-27B-MTPLX-Optimized-Speed" # Calling the OpenAI-compatible server with curl curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Youssofal/Qwen3.6-27B-MTPLX-Optimized-Speed", "messages": [ {"role": "user", "content": "Hello"} ] }'
| { | |
| "arch_id": "qwen3-next-mtp", | |
| "artifact_role": "maximum-speed-flat4-candidate", | |
| "base_trunk": "mlx-community/Qwen3.6-27B-4bit", | |
| "exactness_baseline": { | |
| "attention_impl": "mlx_vector_paged", | |
| "context": 64, | |
| "gate": "phase0h-paged-verifier-exactness", | |
| "max_abs_diff": 0.0, | |
| "mode": "decode-from-stock-prefix", | |
| "sample_agreement": 1.0, | |
| "status": "passed", | |
| "topk_overlap_ratio": 1.0, | |
| "total_variation": 0.0, | |
| "verify_tokens": 4 | |
| }, | |
| "mtp_depth_max": 3, | |
| "mtp_sidecar": "Qwen3.6-27B-MTPLX-CyanKiwi-Packed-BF16-INT4-v3", | |
| "mtplx_version": "0.1.0-preview", | |
| "recommended_draft_lm_head": { | |
| "bits": 3, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "recommended_draft_sampler": { | |
| "temperature": 0.7, | |
| "top_k": 20, | |
| "top_p": 0.95 | |
| }, | |
| "recommended_profile": "performance-cold", | |
| "sampler": { | |
| "temperature": 0.6, | |
| "top_k": 20, | |
| "top_p": 0.95 | |
| }, | |
| "speed_evidence": { | |
| "acceptance_by_depth": [ | |
| 1.0, | |
| 0.9795918367346939, | |
| 0.9387755102040817 | |
| ], | |
| "accepted_by_depth": [ | |
| 49, | |
| 48, | |
| 46 | |
| ], | |
| "artifacts": [ | |
| "/Users/youssof/.mtplx/fanmax_flat4_draft_temp070_cleanapps_20260503-230229.json", | |
| "/Users/youssof/.mtplx/fanmax_flat4_draft_temp070_cleanapps_repeat_20260503-230458.json" | |
| ], | |
| "correction_tokens": 3, | |
| "depth": 3, | |
| "draft_lm_head": "3-bit affine group64 draft-only head", | |
| "draft_sampler": { | |
| "temperature": 0.7, | |
| "top_k": 20, | |
| "top_p": 0.95 | |
| }, | |
| "drafted_by_depth": [ | |
| 49, | |
| 49, | |
| 49 | |
| ], | |
| "enable_thinking": false, | |
| "greedy_diagnostic": { | |
| "accepted_by_depth": [ | |
| 49, | |
| 49, | |
| 43 | |
| ], | |
| "artifact": "/Users/youssof/.mtplx/fanmax_flat4_full_greedy_cleanapps_20260503-230229.json", | |
| "correction_tokens": 0, | |
| "draft_sampler": { | |
| "temperature": 0.0, | |
| "top_k": 0, | |
| "top_p": 1.0 | |
| }, | |
| "drafted_by_depth": [ | |
| 51, | |
| 51, | |
| 51 | |
| ], | |
| "target_sampler": { | |
| "temperature": 0.0, | |
| "top_k": 0, | |
| "top_p": 1.0 | |
| }, | |
| "tok_s": 60.108346853627076, | |
| "verify_calls": 51 | |
| }, | |
| "older_3bit_artifacts": [ | |
| "/Users/youssof/.mtplx/fanmax_flat4_cyankiwi_draft_head_3bit_isolated_20260503.json", | |
| "/Users/youssof/.mtplx/fanmax_flat4_cyankiwi_draft_head_3bit_repeat_20260503.json" | |
| ], | |
| "older_3bit_tok_s": [ | |
| 60.03822277200243, | |
| 60.06063543439426 | |
| ], | |
| "previous_best_artifacts": [ | |
| "/Users/youssof/.mtplx/fanmax_flat4_draft_temp070_optimized_env_20260503.json", | |
| "/Users/youssof/.mtplx/fanmax_flat4_draft_temp070_repeat_optimized_env_20260503.json" | |
| ], | |
| "previous_best_tok_s": [ | |
| 61.52744855840259, | |
| 60.89966247416089 | |
| ], | |
| "production_cli_contract_checks": [ | |
| { | |
| "artifact": "/Users/youssof/.mtplx/fanmax_mtplx_flat4_cyankiwi_cli_contract_perfcold_disablethinking_20260503.json", | |
| "tok_s": 59.51602930081416 | |
| }, | |
| { | |
| "artifact": "/Users/youssof/.mtplx/fanmax_mtplx_flat4_cyankiwi_cli_contract_perfcold_disablethinking_repeat_20260503.json", | |
| "tok_s": 59.97165246907193 | |
| } | |
| ], | |
| "profile": "performance-cold", | |
| "timestamp": "2026-05-03T23:07:00+0100", | |
| "tok_s": [ | |
| 63.05651084048216, | |
| 62.885564723941826 | |
| ], | |
| "verify_calls": 49 | |
| }, | |
| "verified_on": { | |
| "hardware": "Apple M5 Max, 128 GB unified memory", | |
| "machine_arch": "arm64", | |
| "model": "Qwen3.6-27B-MTPLX-Flat4-CyanKiwiMTP", | |
| "timestamp": "2026-05-03T17:49:00+0100" | |
| } | |
| } | |