Exl2
Collection
Models that we have quantized to exllamav2's quantization format • 22 items • Updated • 2
Aetheria-L2-70B-exl2
Exllama v2 quant of royallab/Aetheria-L2-70B
Branches:
- main: measurement.json calculated at 2048 token calibration rows on PIPPA
- 5.0bpw-h6: 5 decoder bits per weight, 6 head bits
- ideal for 2x 24gb GPUs at 8192 context, or 1x 48gb GPU at 8192 context with CFG cache