FRAMEWIREIndonesiaUpdated Sep 21Live wire
0:00 / 0:00

Found a sweet spot between quality and speed for Qwen 3.8 Flash on 2x3090s @ 3.5bpw, running some tests

Backend is exllamav3, running pretty sweet @ around 105 tk/s average (92 tk/s prose/reasoning, 105 tk/s coding and 120 tk/s file editing) and 1635 tk/s prefill

VieirowskiSep 2137
0:00 / 0:00

RTX 3060でQwen 3.8 Flash Next

net58264Sep 21
0:00 / 0:00

DeepSeek V4 Flash, Qwen 3.8 27B, GLM 5.2, Nemotron 3 Ultra, Laguna S 2.1, and Jev for agent routing.

All FREE: OpenRouter: DeepSeek paths, Qwen 3.8 27B, GLM 5.2, Ling 3.0 Flash VL, Laguna S 2.1, Nemotron 3.5 Lightning / 3 Ultra: OpenCode Zen:

ZEFISep 2173
0:00 / 0:00

Qwen 3.8 Max Full COURSE 1 HOUR (Build & Automate Anything)

Want the SOP? DM me. 💬

Julian Goldie SEOSep 213