Instructions to use rapid-mlx/Qwen3.8-27B-4bit-MTP-MLX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rapid-mlx/Qwen3.8-27B-4bit-MTP-MLX 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("rapid-mlx/Qwen3.8-27B-4bit-MTP-MLX")

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 rapid-mlx/Qwen3.8-27B-4bit-MTP-MLX with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "rapid-mlx/Qwen3.8-27B-4bit-MTP-MLX"

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": "rapid-mlx/Qwen3.8-27B-4bit-MTP-MLX"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use rapid-mlx/Qwen3.8-27B-4bit-MTP-MLX with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "rapid-mlx/Qwen3.8-27B-4bit-MTP-MLX"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "rapid-mlx/Qwen3.8-27B-4bit-MTP-MLX"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "rapid-mlx/Qwen3.8-27B-4bit-MTP-MLX",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use rapid-mlx/Qwen3.8-27B-4bit-MTP-MLX 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 "rapid-mlx/Qwen3.8-27B-4bit-MTP-MLX"

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 rapid-mlx/Qwen3.8-27B-4bit-MTP-MLX

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use rapid-mlx/Qwen3.8-27B-4bit-MTP-MLX with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "rapid-mlx/Qwen3.8-27B-4bit-MTP-MLX"

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 "rapid-mlx/Qwen3.8-27B-4bit-MTP-MLX" \
  --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"

Qwen3.8-27B 4-bit MLX + MTP

An official Rapid-MLX, self-contained MLX package of Qwen3.8-27B. It includes both the 4-bit target weights and the matching native Multi-Token Prediction (MTP) drafter in model-mtp.safetensors.

Users download one repository; the target and acceleration weights stay paired. The MTP weights were derived from the same upstream Qwen checkpoint as the target. Upstream model license and limitations continue to apply.

Rapid-MLX

Use a Rapid-MLX release that supports Qwen3.8 native MTP. Rapid can load the target and use the colocated model-mtp.safetensors as its MTP sidecar. MTP is speculative decoding: accepted output remains identical to greedy autoregressive decoding. Runtime should fall back to autoregressive decoding when MTP is unavailable or is not beneficial on the current Mac.

rapidmlx serve rapid-mlx/Qwen3.8-27B-4bit-MTP-MLX \
  --speculative-config '{"method":"mtp","model":"rapid-mlx/Qwen3.8-27B-4bit-MTP-MLX"}'

Validation

On an Apple-silicon Studio test system, a paired greedy smoke test produced the same emitted-token hash with and without MTP. One measured prompt ran at 39.66 tok/s autoregressive and 46.73 tok/s with Rapid MTP (1.18x). Performance varies by prompt and hardware; this is a compatibility result, not a universal speed claim.

model-*.safetensors: Qwen3.8-27B MLX 4-bit target weights
model-mtp.safetensors: matching MLX 4-bit native MTP drafter
tokenizer, processor, generation, and model configuration files

The target is based on mlx-community/Qwen3.8-27B-4bit; the MTP drafter is based on mlx-community/Qwen3.8-27B-MTP-4bit. Both originate from Qwen/Qwen3.8-27B.

Downloads last month: 502

Safetensors

Model size

5B params

Tensor type

BF16

U32

MLX

Hardware compatibility

4-bit

Model tree for rapid-mlx/Qwen3.8-27B-4bit-MTP-MLX

Base model

Qwen/Qwen3.8-27B

Quantized

(810)

this model

rapid-mlx
/

Qwen3.8-27B-4bit-MTP-MLX

Qwen3.8-27B 4-bit MLX + MTP

Rapid-MLX

Validation

Contents

Model tree for rapid-mlx/Qwen3.8-27B-4bit-MTP-MLX