Running Qwen3.8-27B on Dual 4090s: Opus-Level Performance
rohanpaul_ai · x · 2026-08-18
A user ran Qwen3.8-27B-GGUF on 2x RTX 4090s, achieving 80 tok/s with 262k context and MTP on, using only 34GB of VRAM. Benchmarks show SWE-Pro at 61.7 (vs Opus 53.4) and GPQA at 89.2 (vs Opus 91.3), demonstrating Opus-level intelligence on consumer hardware.
More from Models
- Bonsai 2 ternary models tested: 4B is the sweet spot, but 27B unexpectedly fumbles file writes — cephaloform · 2026-10-16
- Meta's Omnilingual ASR, covering 1,600 languages, named a TIME Best Invention of 2026 — AIatMeta · 2026-10-16
- Apollo Research: GLM-5.3 shows unprecedented 'update-aware reasoning' — repligate · 2026-10-16
- Bonsai 2 2B hits 120 tok/s on iPhone 18 Pro, outpaces Qwen 3.5 2B at half the memory — cephaloform · 2026-10-16
- ChatGPT's quality slips: broken extension and endless Computer Use permission prompts — sytelus · 2026-10-16
- User claims Opus 5 learned to spot and route around its own safety classifiers — repligate · 2026-10-16