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

Libraries

How to use DreamFoundries/Qwen3.8-27B-8bit 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("DreamFoundries/Qwen3.8-27B-8bit")

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 DreamFoundries/Qwen3.8-27B-8bit with Pi:

Start the MLX server

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

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": "DreamFoundries/Qwen3.8-27B-8bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use DreamFoundries/Qwen3.8-27B-8bit with OpenClaw:

Start the MLX server

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

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 "DreamFoundries/Qwen3.8-27B-8bit" \
  --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 DreamFoundries/Qwen3.8-27B-8bit with MLX LM:

Generate or start a chat session

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

Run an OpenAI-compatible server

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

Hermes Agent

How to use DreamFoundries/Qwen3.8-27B-8bit 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 "DreamFoundries/Qwen3.8-27B-8bit"

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 DreamFoundries/Qwen3.8-27B-8bit

Run Hermes

hermes

Atomic Chat

Qwen3.8-27B 8-bit MLX

MLX conversion of Qwen/Qwen3.8-27B, quantized with mlx-lm 0.31.3 using affine 8-bit weights and group size 64 (8.501 effective bits per weight). The safetensors weights occupy approximately 27 GB.

Comparative quality and performance benchmarks are not available for this conversion.

Use with mlx

from mlx_lm import load, generate

model, tokenizer = load("DreamFoundries/Qwen3.8-27B-8bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)

Downloads last month: 83

Safetensors

Model size

8B params

Tensor type

BF16

U32

MLX

Hardware compatibility

8-bit

Model tree for DreamFoundries/Qwen3.8-27B-8bit

Base model

Qwen/Qwen3.8-27B

Quantized

(355)

this model

Collection including DreamFoundries/Qwen3.8-27B-8bit

Qwen3.8 MLX Quants

Collection

MLX affine 4-bit, 6-bit, and 8-bit quantizations of Qwen/Qwen3.8-27B. • 3 items • Updated 1 day ago