🖼️00Running a 35B MoE (Qwen3.6-35B-A3B) on 2x GTX 1080 Ti in 2026 — Real Benchmarks, and Does the Second GPU Actually Help?DEV Community: machinelearning·byeongsoo kang·4 months ago#Pp28NVQa#dev#model#iq4_xs#ollama#quant#experts+3 more🧰Tag tools✨Add tagI benchmarked Qwen3.6-35B-A3B (IQ4_XS) on two 8-year-old GTX 1080 Ti cards: ~20 tok/s, and the second GPU only adds ~20% (not 2x). Real numbers, VRAM math, and why a 35B fits 22GB.15s0Read later0Read More
