Special request. Quantized from fp16 with love. Please note I have not tested context to the full 32k, but these quants have all passed the standard suite of coherence and KL-divergence benchmark tests. Any feedback is welcomed.
Quantizations made possible using .imatrix file from this repo (special thanks to ikawrakow again)
For a brief rundown of iMatrix quant performance please see this PR
All quants are verified working prior to uploading to repo for your safety and convenience.
Importance matrix quantizations are a work in progress, IQ3 and above is recommended for best results.
Tip: Pick a size that can fit in your GPU while still allowing some room for context for best speed. You may need to pad this further depending on if you are running image gen or TTS as well.
