Instructions to use mlx-community/Qwen3.8-Flash-Next-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mlx-community/Qwen3.8-Flash-Next-4bit with MLX:

# Make sure mlx-vlm is installed
# pip install --upgrade mlx-vlm

from mlx_vlm import load, generate
from mlx_vlm.prompt_utils import apply_chat_template
from mlx_vlm.utils import load_config

# Load the model
model, processor = load("mlx-community/Qwen3.8-Flash-Next-4bit")
config = load_config("mlx-community/Qwen3.8-Flash-Next-4bit")

# Prepare input
image = ["http://images.cocodataset.org/val2017/000000039769.jpg"]
prompt = "Describe this image."

# Apply chat template
formatted_prompt = apply_chat_template(
    processor, config, prompt, num_images=1
)

# Generate output
output = generate(model, processor, formatted_prompt, image)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use mlx-community/Qwen3.8-Flash-Next-4bit with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "mlx-community/Qwen3.8-Flash-Next-4bit"

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": "mlx-community/Qwen3.8-Flash-Next-4bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent

How to use mlx-community/Qwen3.8-Flash-Next-4bit 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 "mlx-community/Qwen3.8-Flash-Next-4bit"

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 mlx-community/Qwen3.8-Flash-Next-4bit

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use mlx-community/Qwen3.8-Flash-Next-4bit with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "mlx-community/Qwen3.8-Flash-Next-4bit"

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 "mlx-community/Qwen3.8-Flash-Next-4bit" \
  --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-Flash-Next-4bit (MLX)

4-bit MLX conversion of Qwen/Qwen3.8-Flash-Next, converted with mlx-vlm main (post-#2032) at commit d1bd74ed, group size 32.

Group size 32 is required so the PLE n-gram embedding dimensions can be quantized.

Usage

pip install git+https://github.com/Blaizzy/mlx-vlm
mlx_vlm.generate --model mlx-community/Qwen3.8-Flash-Next-4bit \
  --prompt "Explain sparse attention in one paragraph." --max-tokens 256

Why this conversion exists

Qwen4ExpRMSNorm applies 1 + w to norm gains that the released checkpoint stores centered at zero, matching upstream Qwen4ExpTextRMSNorm. Several MLX conversions published before #2032 landed were made with a converter that folded that +1 into the saved weights, so loading them applies the offset twice and generation degenerates into noise (#2041).

Verification

Checked against the bf16 source after conversion:

check	result
source integrity	131/131 shards, tensor bytes byte-exact vs `index total_size`
norm gain center (source vs converted)	`+0.2216` vs `+0.2216`, delta `+0.00000`
norm tensors bit-identical	148 / 148
`sanitize()` idempotence	passes over 480 1-D tensors
generation	coherent output at `--temperature 0.0`

A gain center near +1.15 instead of +0.22 is the signature of the double-shifted conversions described above.

Downloads last month: 1,863

Safetensors

Model size

177B params

Tensor type

U32

BF16

I64

MLX

Hardware compatibility

4-bit

Model tree for mlx-community/Qwen3.8-Flash-Next-4bit

Base model

Qwen/Qwen3.8-Flash-Next

Quantized

(173)

this model

Quantizations

1 model