Issues / #621

#621 Please add Unsloth Qwen3.8-Flash-Next-UD-IQ4_XS

closed · @Almazick · 3 comments · View on GitHub

Models & quants

Description

Please add model Unsloth Qwen3.8-Flash-Next-UD-IQ4_XS

Reason:  model UD-Q4_K_XL is too big.  IQ3_S is fast but much dumber.  We need something in the middle ground, such as UD-IQ4_XS .  It makes a huge difference.  

Related on strata.com

Editorial links to help you install, pick models, or read release notes — not part of the upstream thread.