Phi-4-multimodal-instruct-FP8
nvidia/Phi-4-multimodal-instruct-FP8
- kind
- fp8
- quant
- fp8 (8-bit)
- family
- phi
- modality
- —
- root model
- microsoft/Phi-4-multimodal-instruct
- provider
- nvidia
- license
- other
- language
- —
- context
- 128K
- library
- Model Optimizer
- vRAM (GB)
- —
- size on disk
- —
- downloads
- 296
- likes
- 7
- created
- —
- last modified
- 2025-09-05T05:13:38+00:00 (2025)
- huggingface
- https://huggingface.co/nvidia/Phi-4-multimodal-instruct-FP8
- tags
- Model Optimizersafetensorsphi4mmnvidiaModelOptPhi4quantizedFP8fp8custom_codebase_model:microsoft/Phi-4-multimodal-instructbase_model:quantized:microsoft/Phi-4-multimodal-instructlicense:othermodeloptregion:us
Benchmark scores (0)
no scores extracted for this variant.
Discussions (0)
none scraped.