Video-Text-to-Text
Transformers
Safetensors
English
Chinese
moss_vl
feature-extraction
MOSS-VL
image-understanding
video-understanding
bitsandbytes
NF4
quantized
custom_code
4-bit precision
Instructions to use OpenMOSS-Team/MOSS-VL-Instruct-0708-NF4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use OpenMOSS-Team/MOSS-VL-Instruct-0708-NF4 with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("OpenMOSS-Team/MOSS-VL-Instruct-0708-NF4", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "created_at": "2026-08-11T04:18:07.460954+00:00", | |
| "source_model": "/inspire/qb-ilm/project/video-understanding/public/train/moss_vl_streaming/8B/final_release/MOSS-VL-0708-Instruct-sglang", | |
| "output_dir": "/inspire/qb-ilm/project/video-understanding/public/train/moss_vl_streaming/8B/final_release/quant/MOSS-VL-0708-Instruct-SGLang-NF4-KV8", | |
| "runtime": "native SGLang MOSS-VL", | |
| "weight_format": "bitsandbytes NF4 W4A16 keep-first-last-4", | |
| "quantized_linear_count": 240, | |
| "kv_cache": "native SGLang FP8 E4M3 via runtime argument", | |
| "tp_support": "prequantized bitsandbytes is TP1 only in current SGLang", | |
| "peak_gpu_memory_gib_during_conversion": 11.038, | |
| "versions": { | |
| "torch": "2.8.0+cu128", | |
| "transformers": "4.57.1", | |
| "bitsandbytes": "0.49.2" | |
| } | |
| } | |