Instructions to use Jundot/Qwen3.8-27B-oQ3.5e-mtp with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use Jundot/Qwen3.8-27B-oQ3.5e-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("Jundot/Qwen3.8-27B-oQ3.5e-mtp") config = load_config("Jundot/Qwen3.8-27B-oQ3.5e-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 Jundot/Qwen3.8-27B-oQ3.5e-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 "Jundot/Qwen3.8-27B-oQ3.5e-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": "Jundot/Qwen3.8-27B-oQ3.5e-mtp" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent
How to use Jundot/Qwen3.8-27B-oQ3.5e-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 "Jundot/Qwen3.8-27B-oQ3.5e-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 Jundot/Qwen3.8-27B-oQ3.5e-mtp
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use Jundot/Qwen3.8-27B-oQ3.5e-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 "Jundot/Qwen3.8-27B-oQ3.5e-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 "Jundot/Qwen3.8-27B-oQ3.5e-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"
Qwen3.8-27B-oQ3.5e-mtp
Updated 2026-11-19: Re-quantized with the refined oQe rounding in oMLX 0.8.0, which lowers quantization error at the same size and speed. Please re-download if you have an earlier copy.
This model was quantized using oQ (oMLX v0.8.0) mixed-precision quantization with improved oQe (jundot/omlx#4930) and oQe rounding refinement (jundot/omlx#5292).
A mixed-precision MLX checkpoint of Qwen/Qwen3.8-27B, a 27B dense vision-language model built on the Qwen3.5 architecture, with a hybrid layout of Gated DeltaNet and Gated Attention layers, image and video understanding and a 262,144-token native context. It includes the language model, the vision encoder and the multi-token prediction (MTP) head.
The effective average is 4.070 bits/weight for the language backbone and 4.297 bits/weight for the complete checkpoint.
Quantization and Bit Distribution
oQ3.5e allocates bits by measured layer sensitivity, then rounds each group with an importance matrix (128 samples x 512 tokens) and a weighted least-squares refit of its scale and bias.
| Storage format | Logical weights | Share of total | Tensor storage | Effective bits/weight |
|---|---|---|---|---|
| Affine 3-bit, group 64 | 18.403B | 66.240% | 7.498 GiB | 3.50 |
| Affine 4-bit, group 64 | 3.316B | 11.936% | 1.737 GiB | 4.50 |
| Affine 5-bit, group 64 | 4.275B | 15.387% | 2.737 GiB | 5.50 |
| Affine 6-bit, group 64 | 1.272B | 4.578% | 0.962 GiB | 6.50 |
| Affine 8-bit, group 64 | 0.000B | 0.001% | 0.000 GiB | 8.50 |
| BF16 | 0.516B | 1.857% | 0.961 GiB | 16.00 |
| Total | 27.781B | 100% | 13.896 GiB | 4.297 |
Storage Breakdown
| Component | Logical weights | Storage |
|---|---|---|
| Language backbone | 26.896B | 13.685 GB / 12.745 GiB |
| Vision encoder | 0.461B | 0.921 GB / 0.858 GiB |
| MTP head | 0.425B | 0.314 GB / 0.293 GiB |
| Total | 27.781B | 14.921 GB / 13.896 GiB |
License
Apache-2.0, following the source model. See LICENSE.
- Downloads last month
- 779
3-bit
Model tree for Jundot/Qwen3.8-27B-oQ3.5e-mtp
Base model
Qwen/Qwen3.8-27B