Quantization publisher
fairy322
fairy322 publishes 164 quantizations across 7 models in our index, averaging 5.063 effective bits per weight.
From the file· summed file bytes
Repositories
7
Quantizations
164
Models covered
7
Avg effective bpw
5.063
across their files
Models they publish
| Model | Quantizations | Smallest |
|---|---|---|
| Total04-DeepSeek-R1-Distill-Llama-70B-heretic | 23 | 14.29 GiB |
| Seed-OSS-36B-Instruct-biprojected-norm-preserving-abliterated | 23 | 7.50 GiB |
| OpenAI-gpt-oss-20B-Claude-4.5-Opus-Heretic-Uncensored | 23 | 11.19 GiB |
| Qwen3-VL-8B-Instruct-Heretic | 24 | 3.94 GiB |
| DeepSeek-R1-Distill-Llama-8B-Abliterated | 24 | 3.76 GiB |
| DeepSeek-R1-Distill-Qwen-32B-heretic | 23 | 6.77 GiB |
| L3.1-Dark-Reasoning-LewdPlay-evo-Hermes-R1-Uncensored-8B | 24 | 1.88 GiB |