48 GB VRAM
Collection
Quants that run fast on 2x3090 consuming 48GB total VRAM.
•
2 items
•
Updated
exllamav2 quant for fixed version of mattshumer/Reflection-Llama-3.1-70B
Runs smoothly on 2x3090 with 48GB VRAM
All comments are greatly appreciated, download, test and if you appreciate my work, consider buying me my fuel:
- Downloads last month
- 8
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The model has no library tag.