Quantization publisher
Aashraf995
Aashraf995 publishes 1 quantizations across 1 models in our index, averaging 8.600 effective bits per weight.
From the file· summed file bytes
Repositories
1
Quantizations
1
Models covered
1
Avg effective bpw
8.600
across their files
Models they publish
| Model | Quantizations | Smallest |
|---|---|---|
| KaLM-embedding-multilingual-mini-instruct-v2.5 | 1 | 0.49 GiB |