Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
TeeZee
's Collections
Heretic models
24 GB VRAM
Kyllene
Dark Forests
Buttocks
12 GB VRAM
Writing style transfer experiments
15 GB Colab
Workbench
Polish speaking LLMs
LASERS
BigMaid
48 GB VRAM
48 GB VRAM
updated
Sep 9, 2024
Quants that run fast on 2x3090 consuming 48GB total VRAM.
Upvote
-
TeeZee/Reflection-Llama-3.1-70B-GGUF
71B
•
Updated
Sep 10, 2024
•
12
•
1
TeeZee/Reflection-Llama-3.1-70B-bpw4.0-h8-exl2
Updated
Sep 9, 2024
•
4
•
2
Upvote
-
Share collection
View history
Collection guide
Browse collections
