#+HashtagPLUS#Hashtag the Web... #Tag your World!

Import Manifesto Woburn Center

Menu

#Iq4_xs

2 posts

Feed·

Images only2 of 2 posts

I changed one llama.cpp flag, and my 8GB laptop GPU now runs a 35B model faster than I can read

🖼️

I changed one llama.cpp flag, and my 8GB laptop GPU now runs a 35B model faster than I can read

XDA ·Abhinav Raj·5 days ago

#xdadevelopers #xda-developers #llama #model #models

View the full article

Create a free account to read full articles inline — no redirect to the original site.

Create account Log in

Running a 35B MoE (Qwen3.6-35B-A3B) on 2x GTX 1080 Ti in 2026 — Real Benchmarks, and Does the Second GPU Actually Help?

🖼️

Running 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·5 months ago

#dev #model #iq4_xs #ollama #quant

I 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.

15s