Text Generation
MLX
Safetensors
qwen3_5
mtplx
quantized
multi-token-prediction
speculative-decoding
qwen3.5
apple-silicon
conversational
4-bit precision
Instructions to use johninthepool/Qwen3.8-27B-MTPLX-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use johninthepool/Qwen3.8-27B-MTPLX-4bit 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("johninthepool/Qwen3.8-27B-MTPLX-4bit") 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 johninthepool/Qwen3.8-27B-MTPLX-4bit with Pi:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "johninthepool/Qwen3.8-27B-MTPLX-4bit"
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": "johninthepool/Qwen3.8-27B-MTPLX-4bit" } ] } } }Run Pi
# Start Pi in your project directory: pi
- MLX LM
How to use johninthepool/Qwen3.8-27B-MTPLX-4bit with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Interactive chat REPL mlx_lm.chat --model "johninthepool/Qwen3.8-27B-MTPLX-4bit"
Run an OpenAI-compatible server
# Install MLX LM uv tool install mlx-lm # Start the server mlx_lm.server --model "johninthepool/Qwen3.8-27B-MTPLX-4bit" # Calling the OpenAI-compatible server with curl curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "johninthepool/Qwen3.8-27B-MTPLX-4bit", "messages": [ {"role": "user", "content": "Hello"} ] }' - Hermes Agent
How to use johninthepool/Qwen3.8-27B-MTPLX-4bit 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 "johninthepool/Qwen3.8-27B-MTPLX-4bit"
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 johninthepool/Qwen3.8-27B-MTPLX-4bit
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use johninthepool/Qwen3.8-27B-MTPLX-4bit with OpenClaw:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "johninthepool/Qwen3.8-27B-MTPLX-4bit"
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 "johninthepool/Qwen3.8-27B-MTPLX-4bit" \ --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/misterj/models/Qwen3.8-27B", | |
| "exactness_baseline": {}, | |
| "forge_provenance": { | |
| "forge_inputs": { | |
| "mtp_source_path": "/Users/misterj/models/Qwen3.8-27B", | |
| "trunk_path": "/Users/misterj/.mtplx/models/Qwen3.8-27B-MTPLX-4bit" | |
| }, | |
| "forge_recipe": { | |
| "body_bits": 4, | |
| "body_dtype": "bf16", | |
| "body_group_size": 64, | |
| "body_mode": "affine", | |
| "mtp_policy": "keep_bf16" | |
| }, | |
| "forged_at": "2026-08-14T17:55:58+02:00", | |
| "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": "2.3.0", | |
| "published_to_hf": null, | |
| "source_format": "bf16_native", | |
| "source_repo": "/Users/misterj/models/Qwen3.8-27B", | |
| "source_sha": null | |
| }, | |
| "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_max": 3, | |
| "mtp_sidecar": "bf16", | |
| "mtplx_version": "2.3.0", | |
| "recommended_profile": "sustained", | |
| "sampler": { | |
| "temperature": 0.6, | |
| "top_k": 20, | |
| "top_p": 0.95 | |
| }, | |
| "speed_evidence": { | |
| "acceptance_by_depth": [ | |
| 0.9589552238805971, | |
| 0.8955223880597015, | |
| 0.8171641791044776 | |
| ], | |
| "acceptance_collapsed": [], | |
| "depth": 3, | |
| "failure_reasons": [], | |
| "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": 28.717776509308745, | |
| "verify_time_s": 52.947950625093654 | |
| }, | |
| { | |
| "acceptance_by_position": [ | |
| 0.9694835680751174 | |
| ], | |
| "depth": 1, | |
| "finish_reasons": { | |
| "stop": 1 | |
| }, | |
| "hit_token_budget": false, | |
| "hit_token_budget_count": 0, | |
| "multiplier_vs_ar": 1.39154960853895, | |
| "quality_passed": true, | |
| "tok_s": 39.96221065963764, | |
| "verify_time_s": 19.50398992386181 | |
| }, | |
| { | |
| "acceptance_by_position": [ | |
| 0.9612756264236902, | |
| 0.9066059225512528 | |
| ], | |
| "depth": 2, | |
| "finish_reasons": { | |
| "stop": 1 | |
| }, | |
| "hit_token_budget": false, | |
| "hit_token_budget_count": 0, | |
| "multiplier_vs_ar": 1.4245269588461795, | |
| "quality_passed": true, | |
| "tok_s": 40.90924683562984, | |
| "verify_time_s": 27.189730044687167 | |
| }, | |
| { | |
| "acceptance_by_position": [ | |
| 0.9589552238805971, | |
| 0.8955223880597015, | |
| 0.8171641791044776 | |
| ], | |
| "depth": 3, | |
| "finish_reasons": { | |
| "stop": 1 | |
| }, | |
| "hit_token_budget": false, | |
| "hit_token_budget_count": 0, | |
| "multiplier_vs_ar": 1.4956510481915828, | |
| "quality_passed": true, | |
| "tok_s": 42.951772537879236, | |
| "verify_time_s": 22.20622452243697 | |
| } | |
| ], | |
| "greedy_diagnostic": { | |
| "tok_s": 28.717776509308745 | |
| }, | |
| "quality_rejected": [], | |
| "tok_s": [ | |
| 42.951772537879236 | |
| ], | |
| "verdict": "mtp_depth_wins" | |
| }, | |
| "verified_on": { | |
| "hardware": "macOS-26.5.2-arm64-arm-64bit-Mach-O", | |
| "machine_arch": "arm64", | |
| "macos": "26.5.2", | |
| "model": "Qwen3.8-27B-MTPLX-4bit", | |
| "timestamp": "2026-08-14T17:55:58+02:00" | |
| } | |
| } | |