Instructions to use StargazerLabs/Qwen3.8-32B-Jumbo-3bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use StargazerLabs/Qwen3.8-32B-Jumbo-3bit 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("StargazerLabs/Qwen3.8-32B-Jumbo-3bit")

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 StargazerLabs/Qwen3.8-32B-Jumbo-3bit with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "StargazerLabs/Qwen3.8-32B-Jumbo-3bit"

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": "StargazerLabs/Qwen3.8-32B-Jumbo-3bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use StargazerLabs/Qwen3.8-32B-Jumbo-3bit with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "StargazerLabs/Qwen3.8-32B-Jumbo-3bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "StargazerLabs/Qwen3.8-32B-Jumbo-3bit"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "StargazerLabs/Qwen3.8-32B-Jumbo-3bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use StargazerLabs/Qwen3.8-32B-Jumbo-3bit 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 "StargazerLabs/Qwen3.8-32B-Jumbo-3bit"

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 StargazerLabs/Qwen3.8-32B-Jumbo-3bit

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use StargazerLabs/Qwen3.8-32B-Jumbo-3bit with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "StargazerLabs/Qwen3.8-32B-Jumbo-3bit"

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 "StargazerLabs/Qwen3.8-32B-Jumbo-3bit" \
  --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"

Qwen3.8-32B-Jumbo (3-bit)

3-bit quantization of Qwen3.8-32B-Jumbo.

A 76-layer, 31.9B-parameter model created by transplanting the three most-drifted organs from Qwen3.6-27B into Qwen3.8-27B. See the bf16 model card for the full organ selection methodology.

At 3-bit, the 76-layer Jumbo fits in ~16 GB with speculative decoding — roughly the same memory envelope as a 7B model at bf16, but with 76 layers and 32B-class capability.

Key Stats

Parameters: ~31.9B
Layers: 76
Precision: 3-bit (mlx-lm quantized, group_size 64)
Peak memory: ~16.4 GB (with MTP drafter loaded)
MTP Compatible: ~82% drafter acceptance, ~1.6x speculative decoding speedup

Usage (MLX)

# Standard generation
mlx_vlm.generate \
  --model StargazerLabs/Qwen3.8-32B-Jumbo-3bit \
  --prompt "Your prompt here" --max-tokens 2048

# With MTP speculative decoding (use 4-bit drafter; no 3-bit drafter exists)
mlx_vlm.generate \
  --model StargazerLabs/Qwen3.8-32B-Jumbo-3bit \
  --draft-model mlx-community/Qwen3.8-27B-MTP-4bit \
  --prompt "Your prompt here" --max-tokens 2048

Downloads last month: 347

Safetensors

Model size

4B params

Tensor type

BF16

U32

MLX

Hardware compatibility

3-bit

Model tree for StargazerLabs/Qwen3.8-32B-Jumbo-3bit

Base model

Qwen/Qwen3.8-27B

Finetuned

StargazerLabs/Qwen3.8-32B-Jumbo

Quantized

(3)

this model

Collection including StargazerLabs/Qwen3.8-32B-Jumbo-3bit

Jumbo

Collection

Bigger versions of open weight models • 4 items • Updated 2 days ago

StargazerLabs
/

Qwen3.8-32B-Jumbo-3bit

Qwen3.8-32B-Jumbo (3-bit)

Key Stats

Usage (MLX)

Related

Model tree for StargazerLabs/Qwen3.8-32B-Jumbo-3bit

Collection including StargazerLabs/Qwen3.8-32B-Jumbo-3bit

Jumbo