Instructions to use Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Youssofal/Qwen3.8-27B-MTPLX-Bare-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/Qwen3.8-27B-MTPLX-Bare-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 Settings
LM Studio

How to use Youssofal/Qwen3.8-27B-MTPLX-Bare-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/Qwen3.8-27B-MTPLX-Bare-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/Qwen3.8-27B-MTPLX-Bare-Speed"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed 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"

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" \
  --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"

MLX LM

How to use Youssofal/Qwen3.8-27B-MTPLX-Bare-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/Qwen3.8-27B-MTPLX-Bare-Speed"

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"
# 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",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use Youssofal/Qwen3.8-27B-MTPLX-Bare-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/Qwen3.8-27B-MTPLX-Bare-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/Qwen3.8-27B-MTPLX-Bare-Speed

Run Hermes

hermes

Atomic Chat

MTPLX.COM: 2 to 3x speedup. The fastest way to run models on a Mac.

Qwen 3.8 27B Bare Speed

Quickest burst chat speeds. Lower quality and slower on long coding tasks.

The fastest of the three MTPLX Qwen 3.8 builds and the smallest download. Qwen3.8-27B in flat 4-bit with its native multi-token-prediction head kept, so MTPLX drafts ahead and verifies in one pass. If you want the snappiest chat on a Mac and can live with a rougher quant, this is it. For coding, pick Optimized Speed.

Speeds

Measured on an M5 Max, fans verified at max, single stream, generation running to the model's own stop, official Qwen 3.8 sampling (temperature 1.0, top-p 0.95, top-k 20).

Run	tok/s
Coding task, medium reasoning, `mtplx serve`	65.2
Same task inside the MTPLX Mac app	64.4
Long reasoning at xhigh, 34k and 37k token answers	35.7 and 32.0
One 52,740-token answer, 27.2 minutes, ended at the model's own stop	32.4 sustained

Same night, same task: the previous MTPLX flagship Qwen 3.6 27B Optimized Speed V2 ran 59.9 to 60.1 tok/s. oMLX 0.5.7 serving its own Qwen 3.8 4-bit MTP quant ran 63.3. LM Studio on the 52k-token long answer ran 17.40 tok/s against 32.4 here.

Draft acceptance on the coding task by depth: 0.95, 0.86, 0.78. Verify cost 44 ms per round.

How it is built

Every weight matrix at 4-bit with 64-weight groups. Nothing promoted.
The GDN convolution kernels and recurrent state parameters, every norm, and the whole MTP head stay 16-bit.
KL divergence to the original bf16 model on our coding battery: 0.0376. Optimized Speed is 1.7x closer, Optimized Quality 36x closer. That is the trade you make for the speed.


Download	16.0 GB
Peak unified memory (measured, this artifact)	17.0 GB
Context window	262,144 tokens
MTP depth	3
Sampling	temperature 1.0, top-p 0.95, top-k 20 (the official Qwen 3.8 contract)
Draft sampler	temperature 0.6 (measured winner for this build, 46.1 vs 42.4 tok/s)

The tuned depth and draft settings ship inside mtplx_runtime.json. MTPLX reads them on load. The draft sampler is a speed knob only: MTPLX accepts drafts with the probability-ratio rule plus residual resampling, so the output follows the model's own distribution at any temperature. Reasoning effort levels (xhigh, medium, low) work, and preserved thinking flows through the MTP path.

Use it

Mac app: download at mtplx.com, pick "Qwen 3.8 27B Bare Speed".

Command line:

pip install mtplx
mtplx serve --model Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed

Siblings: Optimized Speed (recommended for coding) and Optimized Quality (8-bit, perfect quality). On an M1 or M2 Mac use the FP16 build of this model.

Downloads last month: 6

Safetensors

Model size

4B params

Tensor type

BF16

U32

MLX

Hardware compatibility

4-bit

Model tree for Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed

Base model

Qwen/Qwen3.8-27B

Quantized

(372)

this model