24GB VRAM Optimal Quants
Collection
When asked what I use locally on a 24GB card, this is what I point to. I favor exl2s for long context, GGUF for very short context.
•
12 items
•
Updated
•
2
Star-Command-R-Lite-32B-v1
A simple SLERP merge of TheDrummer's Star-Command with its base model, to tone it down and "keep" more of Command-R.
4bpw exl2 quantization made for use in exllama on 24GB GPUs.
https://huggingface.co/TheDrummer/Star-Command-R-32B-v1
Created using mergekit.
Merge Details
Merge Method
This model was merged using the SLERP merge method.
Models Merged
The following models were included in the merge:
- TheDrummer/Star-Command-R-32B-v1
- CohereForAI/c4ai-command-r-08-2024
Configuration
The following YAML configuration was used to produce this model:
models:
- model: TheDrummer/Star-Command-R-32B-v1
- model: CohereForAI/c4ai-command-r-08-2024
merge_method: slerp
parameters:
t:
- value: 0.5
base_model: CohereForAI/c4ai-command-r-08-2024
dtype: bfloat16
- Downloads last month
- 25
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.
Model tree for Downtown-Case/Star-Command-R-Lite-32B-v1-exl2-4bpw
Merge model
this model