Edit model card

Mixtral-8x7B-Instruct-v0.1-limarp-exl2

Exllama v2 quant of Doctor-Shotgun/Mixtral-8x7B-Instruct-v0.1-limarp

Branches:

  • main: measurement.json calculated at 2048 token calibration rows on exl2 default calibration dataset
  • 3.5bpw-h6: 3.5 decoder bits per weight, 6 head bits
    • ideal for 24gb VRAM
  • 6.0bpw-h6: 6 decoder bits per weight, 6 head bits
    • ideal for 48gb VRAM
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Examples
Inference API (serverless) has been turned off for this model.