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

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

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"

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

Qwen 3.8 27B Bare Speed FP16

Quickest burst chat speeds. Lower quality and slower on long coding tasks. This is the M1 and M2 build.

The FP16 precision sibling of Qwen 3.8 27B Bare Speed. M1 and M2 Macs do not run bf16 well, so this build keeps every quantized weight byte-identical to the parent and stores the remaining floating tensors (scales, biases, norms, the GDN convolution and state parameters, and the MTP head) in fp16 instead of bf16. Same layout, same tuned depth and draft settings, same context window. On an M3 or newer Mac use the parent instead.

MTPLX picks the right one for you: the app and mtplx start route M1 and M2 Macs to the FP16 builds and everything newer to the parents. Draft sampler temperature 0.6 is stamped in, the measured winner for this build.

Speeds

The numbers we publish for the parent were measured on an M5 Max: 65.2 tok/s on the coding task and 32.4 tok/s sustained over a single 52,740-token answer, official Qwen 3.8 sampling, generation running to the model's own stop. This FP16 build has the same weights and runs the same MTPLX turbo path, so the speculative math is identical; absolute tok/s on an M1 or M2 depends on that chip. We have not published M1 or M2 numbers for it yet.


Download	16.0 GB
Peak unified memory (parent, measured on M5 Max)	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)

MTPLX_FP16_CONVERSION_MANIFEST.json in the repo lists every tensor that was cast and every tensor that was preserved, with sha256 for each shard. Speculation in MTPLX is exact at any temperature: drafts are accepted with the probability-ratio rule plus residual resampling.

Use it

Mac app: download at mtplx.com, pick "Qwen 3.8 27B Bare Speed FP16".

Command line:

pip install mtplx
mtplx serve --model Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed-FP16

The other two FP16 builds: Optimized Speed FP16, Optimized Quality FP16.

Downloads last month: 3,243

Safetensors

Model size

5B params

Tensor type

F16

U32

BF16

MLX

Hardware compatibility

4-bit

Model tree for Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed-FP16

Base model

Qwen/Qwen3.8-27B

Quantized

(725)

this model