Image-Text-to-Text
MLX
Safetensors
zaya1_vl
zaya
mixture-of-experts
hybrid-attention
cca-attention
apple-silicon
reasoning
tool-use
quantized
vision
multimodal
vision-language
qwen2_5_vl-vit
mxfp4
jang
osaurus
conversational
Instructions to use OsaurusAI/ZAYA1-VL-8B-MXFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use OsaurusAI/ZAYA1-VL-8B-MXFP4 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("OsaurusAI/ZAYA1-VL-8B-MXFP4") config = load_config("OsaurusAI/ZAYA1-VL-8B-MXFP4") # 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
- LM Studio
| { | |
| "version": 2, | |
| "weight_format": "mxfp4", | |
| "profile": "MXFP4", | |
| "cache_subtype": "zaya_cca", | |
| "source_model": { | |
| "name": "ZAYA1-VL-8B", | |
| "org": "Zyphra", | |
| "architecture": "zaya1_vl" | |
| }, | |
| "has_vision": true, | |
| "expert_layout": "split_switch_mlp", | |
| "quantization": { | |
| "method": "affine", | |
| "group_size": 32, | |
| "bits": 4, | |
| "embed_bits": 8, | |
| "router_bits": 16 | |
| }, | |
| "capabilities": { | |
| "reasoning_parser": "qwen3", | |
| "tool_parser": "zaya_xml", | |
| "think_in_template": false, | |
| "supports_tools": true, | |
| "supports_thinking": true, | |
| "family": "zaya1_vl", | |
| "modality": "vision", | |
| "cache_type": "hybrid" | |
| } | |
| } | |