24 GB VRAM
Collection
Quants that run fast on single 3090/4090 card with 24GB of VRAM and 4096 context length
•
16 items
•
Updated
•
5
Fimbulvetr-10.7B-v1
exllamav2 quant for Sao10K/Fimbulvetr-10.7B-v1Sao10K/Fimbulvetr-10.7B-v1
Runs smoothly on single 3090 in webui with context length set to 4096, ExLlamav2_HF loader and cache_8bit=True
All comments are greatly appreciated, download, test and if you appreciate my work, consider buying me my fuel:
- Downloads last month
- 1
This model does not have enough activity to be deployed to Inference API (serverless) yet.
Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.