Instructions to use inferencerlabs/Qwen3.8-Flash-Next-MLX-Q4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use inferencerlabs/Qwen3.8-Flash-Next-MLX-Q4 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("inferencerlabs/Qwen3.8-Flash-Next-MLX-Q4")
config = load_config("inferencerlabs/Qwen3.8-Flash-Next-MLX-Q4")

# 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 inferencerlabs/Qwen3.8-Flash-Next-MLX-Q4 with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "inferencerlabs/Qwen3.8-Flash-Next-MLX-Q4"

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": "inferencerlabs/Qwen3.8-Flash-Next-MLX-Q4"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent

How to use inferencerlabs/Qwen3.8-Flash-Next-MLX-Q4 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 "inferencerlabs/Qwen3.8-Flash-Next-MLX-Q4"

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 inferencerlabs/Qwen3.8-Flash-Next-MLX-Q4

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use inferencerlabs/Qwen3.8-Flash-Next-MLX-Q4 with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "inferencerlabs/Qwen3.8-Flash-Next-MLX-Q4"

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 "inferencerlabs/Qwen3.8-Flash-Next-MLX-Q4" \
  --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

See Qwen3.8-Flash-Next in action: demonstration videos

Tested on a M5 Max using Inferencer app v2.3.4

Multimodal inference

~42.9 tokens/s ~97.2 GiB

Q4.5-bit quant typically achieves over 90% accuracy

Quantization (bpw)	Perplexity	Token Accuracy	Missed Divergence
Q3.5	168.0	43.45%	72.57%
Q4.5	1.33593	91.65%	17.28%
Q5.5	1.23437	95.05%	17.28%
Q6.5	1.21875	96.65%	12.03%
Q8.5	1.21875	97.65%	9.92%
Q9	1.20312	97.80%	9.60%
Base	1.20312	100%	0.000%

Perplexity: Measures the confidence for predicting base tokens (lower is better)
Token Accuracy: The percentage of correctly generated base tokens
Missed Divergence: Measures severity of misses; how much the token was missed by

Quantized with a modified version of MLX

For more details see demonstration videos or visit Qwen3.8-Flash-Next.

Disclaimer

We are not the creator, originator, or owner of any model listed. Each model is created and provided by third parties. Models may not always be accurate or contextually appropriate. You are responsible for verifying the information before making important decisions. We are not liable for any damages, losses, or issues arising from its use, including data loss or inaccuracies in AI-generated content.

Downloads last month: -

MLX

Hardware compatibility

Quantized

Model tree for inferencerlabs/Qwen3.8-Flash-Next-MLX-Q4

Base model

Qwen/Qwen3.8-Flash-Next

Quantized

(85)

this model