EXL3 quants of Ling-3.1-flash

⚠️ Requires ExLlamaV3 v1.6.3 (or dev branch)

Plain quants:

2.10 bits per weight
2.60 bits per weight
3.10 bits per weight

(more bitrates and self-calibrated quants to follow)

qb_kld

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for turboderp/Ling-3.1-flash-exl3

Quantized
(8)
this model

Collection including turboderp/Ling-3.1-flash-exl3