Views
No views yet
| Branch | Bits | lm_head bits | VRAM (4k) | VRAM (16k) | VRAM (32k) | Description |
|---|---|---|---|---|---|---|
| 8_0 | 8.0 | 8.0 | 24.8 GB | 26.3 GB | 28.3 GB | Maximum quality that ExLlamaV2 can produce, near unquantized performance. |
| 6_5 | 6.5 | 8.0 | 20.3 GB | 21.8 GB | 23.8 GB | Near unquantized performance at vastly reduced size, recommended. |
| 5_0 | 5.0 | 6.0 | 15.8 GB | 17.3 GB | 19.3 GB | Slightly lower quality vs 6.5. |
| 4_25 | 4.25 | 6.0 | 14.0 GB | 15.5 GB | 17.5 GB | GPTQ equivalent bits per weight, slightly higher quality, great for 16gb cards with 16k context. |
| 3_5 | 3.5 | 6.0 | 11.3 GB | 12.8 GB | 14.8 GB | Lower quality, not recommended, only suitable for 12GB cards. |
git clone --single-branch --branch 6_5 https://huggingface.co/bartowski/Buttercup-4x7B-V2-laser-exl2pip3 install huggingface-hubmain (only useful if you only care about measurement.json) branch to a folder called Buttercup-4x7B-V2-laser-exl2:1mkdir Buttercup-4x7B-V2-laser-exl2
2huggingface-cli download bartowski/Buttercup-4x7B-V2-laser-exl2 --local-dir Buttercup-4x7B-V2-laser-exl2 --local-dir-use-symlinks False--revision parameter:1mkdir Buttercup-4x7B-V2-laser-exl2-6_5
2huggingface-cli download bartowski/Buttercup-4x7B-V2-laser-exl2 --revision 6_5 --local-dir Buttercup-4x7B-V2-laser-exl2-6_5 --local-dir-use-symlinks False1mkdir Buttercup-4x7B-V2-laser-exl2-6.5
2huggingface-cli download bartowski/Buttercup-4x7B-V2-laser-exl2 --revision 6_5 --local-dir Buttercup-4x7B-V2-laser-exl2-6.5 --local-dir-use-symlinks False