Instructions to use ddalcu/Qwen3.8-Flash-Next-MLX-Serve-iQ-MLX-3.3bpw with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ddalcu/Qwen3.8-Flash-Next-MLX-Serve-iQ-MLX-3.3bpw 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("ddalcu/Qwen3.8-Flash-Next-MLX-Serve-iQ-MLX-3.3bpw")

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 ddalcu/Qwen3.8-Flash-Next-MLX-Serve-iQ-MLX-3.3bpw with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "ddalcu/Qwen3.8-Flash-Next-MLX-Serve-iQ-MLX-3.3bpw"

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "ddalcu/Qwen3.8-Flash-Next-MLX-Serve-iQ-MLX-3.3bpw"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use ddalcu/Qwen3.8-Flash-Next-MLX-Serve-iQ-MLX-3.3bpw with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "ddalcu/Qwen3.8-Flash-Next-MLX-Serve-iQ-MLX-3.3bpw"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "ddalcu/Qwen3.8-Flash-Next-MLX-Serve-iQ-MLX-3.3bpw"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "ddalcu/Qwen3.8-Flash-Next-MLX-Serve-iQ-MLX-3.3bpw",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use ddalcu/Qwen3.8-Flash-Next-MLX-Serve-iQ-MLX-3.3bpw 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 "ddalcu/Qwen3.8-Flash-Next-MLX-Serve-iQ-MLX-3.3bpw"

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 ddalcu/Qwen3.8-Flash-Next-MLX-Serve-iQ-MLX-3.3bpw

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use ddalcu/Qwen3.8-Flash-Next-MLX-Serve-iQ-MLX-3.3bpw with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "ddalcu/Qwen3.8-Flash-Next-MLX-Serve-iQ-MLX-3.3bpw"

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 "ddalcu/Qwen3.8-Flash-Next-MLX-Serve-iQ-MLX-3.3bpw" \
  --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"

ddalcu commited on 30 days ago

Commit

2b7da62

verified ·

1 Parent(s): 6c0f0f3

Update README.md

Browse files

Files changed (1) hide show

README.md +4 -0

README.md CHANGED Viewed

@@ -23,10 +23,14 @@ the Qwen4 preview architecture (`model_type: qwen4_exp`), quantized to 3.3 bits
 weight with imatrix calibration so it fits a 64 GB Mac with room for 64k of context.
 52 GB resident. Includes the MTP head and the vision tower (image and video input).
 ```bash
 sudo sysctl iogpu.wired_limit_mb=58000     # 64 GB Macs, once per boot; see below
 mlx-serve --model ddalcu/Qwen3.8-Flash-Next-MLX-Serve-iQ-MLX-3.3bpw --serve --ctx-size 65536
 ```
 If you have 128 GB, use
 [ddalcu/Qwen3.8-Flash-Next-MLX-Serve-mixed-4-8bit](https://huggingface.co/ddalcu/Qwen3.8-Flash-Next-MLX-Serve-mixed-4-8bit)

 weight with imatrix calibration so it fits a 64 GB Mac with room for 64k of context.
 52 GB resident. Includes the MTP head and the vision tower (image and video input).
+Download [MLXServe.com](https://mlxserve.com)
 ```bash
 sudo sysctl iogpu.wired_limit_mb=58000     # 64 GB Macs, once per boot; see below
 mlx-serve --model ddalcu/Qwen3.8-Flash-Next-MLX-Serve-iQ-MLX-3.3bpw --serve --ctx-size 65536
 ```
+(launching mlx-serve via UI is also fine)
 If you have 128 GB, use
 [ddalcu/Qwen3.8-Flash-Next-MLX-Serve-mixed-4-8bit](https://huggingface.co/ddalcu/Qwen3.8-Flash-Next-MLX-Serve-mixed-4-8bit)