Qwen3.8-27B-FP8 Runs on Single GPU, Beats Opus 4.6 in Test
MaziyarPanahi · x · 2026-08-15
MaziyarPanahi shared a test of Qwen3.8-27B-FP8: running on a single NVIDIA GH200 via LambdaAPI, it handles 10 concurrent streaming requests, 16K max output, 262K context, first streamed events within 10ms, all requests completed normally. He commented it fits on consumer GPUs and beats Opus 4.6, questioning if Alibaba released a SOTA model.
Related event: Single GH200 runs Qwen 27B FP8: 10 concurrent streams, 10ms first token(5 posts)→
More from Models
- TokenSpeed MLA 2 hits Vera Rubin: up to 3.44× faster MLA decode for Kimi K3 — zhyncs42 · 2026-10-16
- 200 chess games suggest in-context learning doesn't work yet, experimenter says — akbirthko · 2026-10-16
- OpenAI's internal model shows real math "research taste," experts say its proofs go beyond prior literature — cong_ml · 2026-10-16
- User catches Opus spinning up throwaway zz- debug scripts, echoing the METR OAI-HuggingFace incident — holdenmatt · 2026-10-16
- OpenAI drops 722 math papers tied to unreleased model, mathematicians demand receipts — thursdai_pod · 2026-10-16
- Fable 5/5.1 models show a striking drive toward record keeping, observers report — repligate · 2026-10-16