Instructions to use GBP-DE/Qwen3.8-Flash-Next-oQ4e-WLSRefit-MTP with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use GBP-DE/Qwen3.8-Flash-Next-oQ4e-WLSRefit-MTP 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("GBP-DE/Qwen3.8-Flash-Next-oQ4e-WLSRefit-MTP") config = load_config("GBP-DE/Qwen3.8-Flash-Next-oQ4e-WLSRefit-MTP") # 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
- Pi
How to use GBP-DE/Qwen3.8-Flash-Next-oQ4e-WLSRefit-MTP with Pi:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "GBP-DE/Qwen3.8-Flash-Next-oQ4e-WLSRefit-MTP"
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": "GBP-DE/Qwen3.8-Flash-Next-oQ4e-WLSRefit-MTP" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent
How to use GBP-DE/Qwen3.8-Flash-Next-oQ4e-WLSRefit-MTP 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 "GBP-DE/Qwen3.8-Flash-Next-oQ4e-WLSRefit-MTP"
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 GBP-DE/Qwen3.8-Flash-Next-oQ4e-WLSRefit-MTP
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use GBP-DE/Qwen3.8-Flash-Next-oQ4e-WLSRefit-MTP with OpenClaw:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "GBP-DE/Qwen3.8-Flash-Next-oQ4e-WLSRefit-MTP"
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 "GBP-DE/Qwen3.8-Flash-Next-oQ4e-WLSRefit-MTP" \ --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 โ oQ4e WLSRefit MTP | oMLX 0.7.3 Rebuild
MODEL UPDATE โ November 1, 2026
This repository has been updated in place with a newly quantized checkpoint created using oMLX 0.7.3, replacing the previous oMLX 0.7.1.dev1 build.
What's new:
- Rebuilt with the updated oMLX 0.7.3 quantization pipeline.
- Incorporates the revised oQe calibration implementation, which follows the model-specific forward pass.
- Retains importance-aware oQ4e quantization, Weighted Least-Squares (WLS) Refit, iMatrix guidance and MTP support.
- Preserves non-quantized weights in BF16 where applicable.
oMLX 0.7.3 also introduces precision-allocation improvements for certain model architectures. Their reported quality gains should not be assumed to apply directly to this large MoE checkpoint.
No model-specific accuracy improvement is claimed without controlled testing.
This is an update to the existing repository, not a separate model release. The repository URL remains unchanged.
About this model
An enhanced, importance-aware oQ4e quantization of the original Qwen3.8-Flash-Next, designed for inference on Apple Silicon using compatible oMLX runtimes.
The current checkpoint was quantized with oMLX 0.7.3.
Its objective is to combine efficient memory usage with high fidelity to the original model, while retaining MTP acceleration support.
Quantization features
- oQ4e: Importance-aware quantization with variable precision.
- WLS Refit: Weighted Least-Squares refinement designed to reduce quantization error.
- iMatrix: Importance-guided treatment of model weights.
- MTP: Multi-Token Prediction weights preserved for compatible accelerated decoding.
- BF16: Non-quantized tensors retained in BF16 where applicable.
- Apple Silicon: Intended for use with the oMLX inference engine.
The earlier WLS Refit implementation was associated with approximately 11โ15% lower KL divergence in the developer's quantizer evaluations. This is a historical, architecture-dependent result, not a measured quality improvement of the current checkpoint.
For details about the updated quantization pipeline, see the oMLX 0.7.3 release notes.
Historical testing โ previous oMLX 0.7.1.dev1 build
Important: The following observations relate to the previous oQ4e WLSRefit MTP checkpoint, created with oMLX 0.7.1.dev1.
They are preserved for transparency and historical reference. They must not be interpreted as benchmark results for the new oMLX 0.7.3 rebuild.
Tested and reviewed with GPT-6
The previous checkpoint was evaluated using demanding reasoning and analytical challenges, with its outputs reviewed by GPT-6.
Compared with an earlier oQ4e conversion of the same base model, the previous WLSRefit build showed a noticeable improvement in practical output quality during local testing.
In the 60-question Silbergrat Reasoning Challenge, it demonstrated:
- Strong logical coherence and evidence evaluation.
- Substantially fewer serious reasoning inconsistencies.
- Much better language stability than the earlier conversion.
- Careful handling of uncertainty and competing explanations.
A separate XAGUSD quantitative trading research challenge also demonstrated strong analytical capabilities, producing testable hypotheses without inventing profitability claims.
Historical assessment: The previous WLSRefit build showed promising improvements in practical reasoning quality, particularly for complex, long-form analytical tasks.
These observations were qualitative, not standardized benchmarks. The runtime version also changed, so the observed differences could not be attributed exclusively to WLS Refit.
Current build evaluation
The oMLX 0.7.3 rebuild has not yet been independently evaluated against the previous checkpoint.
No improvement in reasoning accuracy, reliability or language quality is claimed at this time.
Compatibility
Requires a compatible oMLX runtime.
This is an oMLX/oQ checkpoint, not a GGUF model.
Lightning MTP acceleration depends on runtime and configuration support.
Credits and License
- Downloads last month
- 515
4-bit