Someone runs K3 on 80x 5090s, for 20 tok/s
zkmon
12 points
0 comments
July 28, 2026
Related Discussions
Found 5 related stories in 118.9ms across 10,677 title embeddings via pgvector HNSW
- Running Qwen3.8 at 255 tok/s on a single 5090 Ir0n · 12 pts · October 13, 2026 · 66% similar
- Kimi K3 (2.8T) at 1 token/s on a MacBook Pro, streamed from four SSDs Argonautlabs · 247 pts · September 08, 2026 · 60% similar
- Running Qwen3.8-Flash-Next NVFP4 at 184 tok/s on a single RTX 6000 Pro matteohorvath · 14 pts · October 26, 2026 · 54% similar
- Show HN: Running 104GB Qwen3.8-Flash-Next on 48GB Mac with at ~12 tok/s carloslfu · 187 pts · September 01, 2026 · 54% similar
- Run Qwen 3.8 Flash Next (125B) on consumer hardware (RTX 4090) at 100T/s snehesht · 696 pts · October 04, 2026 · 53% similar