Text Generation
MLX
Safetensors
qwen3_5
apple-silicon
macos
m1
m2
fp16
speculative-decoding
multi-token-prediction
qwen
qwen3.8
mtp
mtplx
local-ai
chat
conversational
4-bit precision
Instructions to use Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed-FP16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed-FP16 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/Qwen3.8-27B-MTPLX-Bare-Speed-FP16") 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 Settings
- LM Studio
- Pi
How to use Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed-FP16 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/Qwen3.8-27B-MTPLX-Bare-Speed-FP16"
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/Qwen3.8-27B-MTPLX-Bare-Speed-FP16" } ] } } }Run Pi
# Start Pi in your project directory: pi
- MLX LM
How to use Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed-FP16 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/Qwen3.8-27B-MTPLX-Bare-Speed-FP16"
Run an OpenAI-compatible server
# Install MLX LM uv tool install mlx-lm # Start the server mlx_lm.server --model "Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed-FP16" # Calling the OpenAI-compatible server with curl curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed-FP16", "messages": [ {"role": "user", "content": "Hello"} ] }' - Hermes Agent
How to use Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed-FP16 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/Qwen3.8-27B-MTPLX-Bare-Speed-FP16"
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/Qwen3.8-27B-MTPLX-Bare-Speed-FP16
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed-FP16 with OpenClaw:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed-FP16"
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 "Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed-FP16" \ --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"
| { | |
| "arch_id": "qwen3-next-mtp", | |
| "artifact_role": "forge-local", | |
| "base_trunk": "/Users/youssof/.mtplx/models/Qwen--Qwen3.8-27B", | |
| "exactness_baseline": {}, | |
| "forge_provenance": { | |
| "forge_inputs": { | |
| "mtp_source_path": "/Users/youssof/.mtplx/models/Qwen--Qwen3.8-27B", | |
| "trunk_path": "/Users/youssof/.mtplx/models/Qwen3.8-27B-MTPLX-Bare-Speed" | |
| }, | |
| "forge_recipe": { | |
| "body_bits": 4, | |
| "body_group_size": 64, | |
| "body_mode": "affine", | |
| "mtp_policy": "keep_bf16" | |
| }, | |
| "forged_at": "2026-08-14T08:40:15-07:00", | |
| "forged_locally": true, | |
| "mtp_contract": { | |
| "base_hidden_variant": "post_norm", | |
| "concat_order": "embedding_hidden", | |
| "hidden_variant": "post_norm", | |
| "mtp_position_mode": "local", | |
| "mtp_quant_group_size": 64, | |
| "mtp_quant_mode": "affine" | |
| }, | |
| "mtplx_version": "2.6.0", | |
| "published_to_hf": null, | |
| "source_format": "bf16_native", | |
| "source_repo": "Qwen/Qwen3.8-27B", | |
| "source_sha": "1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0", | |
| "head_quantization": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine", | |
| "policy": "all", | |
| "quantized_at": "2026-08-20T04:49:59Z", | |
| "source_sidecar_bytes": 849400388, | |
| "quantized_sidecar_bytes": 238934226, | |
| "tool": "scripts/build_qwen38_q4head_sidecar.py", | |
| "note": "Structural head quantization of the released sidecar; no calibration, no training. Trunk weights unchanged." | |
| } | |
| }, | |
| "mtp_contract": { | |
| "base_hidden_variant": "post_norm", | |
| "concat_order": "embedding_hidden", | |
| "hidden_variant": "post_norm", | |
| "mtp_position_mode": "local", | |
| "mtp_quant_group_size": 64, | |
| "mtp_quant_mode": "affine" | |
| }, | |
| "mtp_depth_default": 3, | |
| "mtp_depth_max": 6, | |
| "mtp_sidecar": "int4-g64-prequantized", | |
| "mtplx_version": "2.9.0", | |
| "precision_policy": { | |
| "intended_default_for": [ | |
| "m1", | |
| "m2" | |
| ], | |
| "note": "FP16 precision sibling of Qwen3.8-27B-MTPLX-Bare-Speed: byte-identical INT packs, bf16 floats cast to fp16 for M1/M2 Macs. Same tuned depth/draft-sampler stamps as the parent; not a separate speed claim.", | |
| "routing": "mtplx start auto-selects this artifact on M1/M2 Apple Silicon", | |
| "variant": "fp16" | |
| }, | |
| "precision_variant": "fp16", | |
| "public_model_id": "mtplx-qwen38-27b-bare-speed-fp16", | |
| "recommended_draft_sampler": { | |
| "temperature": 1.0, | |
| "top_k": 20, | |
| "top_p": 0.95 | |
| }, | |
| "recommended_profile": "turbo", | |
| "release_validation": { | |
| "dropday_bare_draft_sampler": { | |
| "date": "2026-08-14", | |
| "evidence": "in-contract A/B strict max-fans: 46.1 tok/s (draft 0.6) vs 42.4 (draft 1.0); exactness unaffected (probability-ratio acceptance corrects any draft distribution). App launch preset pins the same 0.6.", | |
| "verdict": "draft_temperature 0.6" | |
| }, | |
| "native_sampling": { | |
| "acceptance_by_depth": [ | |
| 0.9827586206896551, | |
| 0.9655172413793104, | |
| 0.9482758620689655, | |
| 0.896551724137931, | |
| 0.8793103448275862, | |
| 0.7931034482758621 | |
| ], | |
| "decode_tok_s_repeats": [ | |
| 90.76619500629357, | |
| 95.88058748793716 | |
| ], | |
| "depth": 6, | |
| "end_to_end_tok_s_repeats": [ | |
| 86.21504502891067, | |
| 90.85944248298674 | |
| ], | |
| "peak_memory_bytes": 16728221169, | |
| "profile": "turbo", | |
| "sampler": { | |
| "temperature": 1.0, | |
| "top_k": 20, | |
| "top_p": 0.95 | |
| }, | |
| "suite": "cold-long-code-192", | |
| "validations_passed": 2, | |
| "validations_total": 2 | |
| }, | |
| "strict_draft_sampler_ab": { | |
| "acceptance_by_depth_draft_0_6": [ | |
| 0.6886792452830188, | |
| 0.42384887839433294, | |
| 0.23376623376623376 | |
| ], | |
| "acceptance_by_depth_draft_1_0": [ | |
| 0.7490470139771284, | |
| 0.4920534011443102, | |
| 0.28544183089637637 | |
| ], | |
| "accepted_tokens_per_verify_draft_0_6": 1.3423529411764705, | |
| "accepted_tokens_per_verify_draft_1_0": 1.5221799746514575, | |
| "decode_tok_s_draft_0_6": [ | |
| 42.97683083623381, | |
| 42.6065647102868 | |
| ], | |
| "decode_tok_s_draft_1_0": [ | |
| 46.80796966146609, | |
| 45.292323193319085 | |
| ], | |
| "depth": 3, | |
| "max_fans_verified": true, | |
| "prompt": "single-file HTML5 Flappy Bird, xhigh reasoning", | |
| "response_tokens": 2000, | |
| "verdict": "keep_official_draft_sampler_1_0" | |
| } | |
| }, | |
| "sampler": { | |
| "temperature": 1.0, | |
| "top_k": 20, | |
| "top_p": 0.95 | |
| }, | |
| "speed_evidence": { | |
| "depth": 3, | |
| "tok_s": [ | |
| 50.16132899123467 | |
| ], | |
| "acceptance_by_depth": [ | |
| 0.9501557632398754, | |
| 0.881619937694704, | |
| 0.7850467289719626 | |
| ], | |
| "greedy_diagnostic": { | |
| "tok_s": 21.672618440463108 | |
| }, | |
| "forge_verify_rows": [ | |
| { | |
| "acceptance_by_position": [], | |
| "depth": 0, | |
| "finish_reasons": { | |
| "stop": 1 | |
| }, | |
| "hit_token_budget": false, | |
| "hit_token_budget_count": 0, | |
| "multiplier_vs_ar": 1.0, | |
| "quality_passed": true, | |
| "tok_s": 21.672618440463108, | |
| "verify_time_s": 36.76132425002288 | |
| }, | |
| { | |
| "acceptance_by_position": [ | |
| 0.9783549783549783 | |
| ], | |
| "depth": 1, | |
| "finish_reasons": { | |
| "stop": 1 | |
| }, | |
| "hit_token_budget": false, | |
| "hit_token_budget_count": 0, | |
| "multiplier_vs_ar": 1.6570495033453116, | |
| "quality_passed": true, | |
| "tok_s": 35.91260162296184, | |
| "verify_time_s": 12.544884410686791 | |
| }, | |
| { | |
| "acceptance_by_position": [ | |
| 0.980225988700565, | |
| 0.9265536723163842 | |
| ], | |
| "depth": 2, | |
| "finish_reasons": { | |
| "stop": 1 | |
| }, | |
| "hit_token_budget": false, | |
| "hit_token_budget_count": 0, | |
| "multiplier_vs_ar": 2.053854263060501, | |
| "quality_passed": true, | |
| "tok_s": 44.51239977562877, | |
| "verify_time_s": 24.228063414688222 | |
| }, | |
| { | |
| "acceptance_by_position": [ | |
| 0.9501557632398754, | |
| 0.881619937694704, | |
| 0.7850467289719626 | |
| ], | |
| "depth": 3, | |
| "finish_reasons": { | |
| "stop": 1 | |
| }, | |
| "hit_token_budget": false, | |
| "hit_token_budget_count": 0, | |
| "multiplier_vs_ar": 2.314502473664313, | |
| "quality_passed": true, | |
| "tok_s": 50.16132899123467, | |
| "verify_time_s": 22.989872808218934 | |
| } | |
| ], | |
| "quality_rejected": [], | |
| "acceptance_collapsed": [], | |
| "failure_reasons": [], | |
| "verdict": "mtp_depth_wins", | |
| "artifact_fingerprint": "sha256:622ef11f76b446124bac1479881fe40a31d88f62274ee14a66e75c5a239b696a" | |
| }, | |
| "verified_on": { | |
| "timestamp": "2026-08-19T23:12:46-07:00", | |
| "hardware": "macOS-26.3.1-arm64-arm-64bit-Mach-O", | |
| "machine_arch": "arm64", | |
| "macos": "26.3.1", | |
| "model": "Qwen3.8-27B-MTPLX-Bare-Speed-FP16" | |
| } | |
| } | |