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 64.1ms across 6,278 title embeddings via pgvector HNSW
- Kimi K3 (2.8T) at 1 token/s on a MacBook Pro, streamed from four SSDs Argonautlabs · 247 pts · September 08, 2026 · 60% 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
- Show HN: A tiny LLM running at 21,000 tok/s on a $250 FPGA (Live Demo) mikeayles · 12 pts · August 10, 2026 · 53% similar
- Kimi K3 exploited the latest Redis server Alifatisk · 50 pts · July 23, 2026 · 52% similar
- Laguna XS 2.1 33B on a RTX 3090: 296 tok/s peak, 152 tok/s at 256K context GreenGames · 13 pts · July 11, 2026 · 52% similar