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 316.2ms across 15,236 title embeddings via pgvector HNSW
- RTX 5080 and RTX 3090 Setup: 80 Tok/s on Qwen 3.6 27B Q8 iMil · 222 pts · June 13, 2026 · 64% similar
- We got 207 tok/s with Qwen3.5-27B on an RTX 3090 GreenGames · 162 pts · April 20, 2026 · 55% similar
- GateGPT: 56k tokens per second Transformer (KV cache) on FPGA at 80 MHz laxmena · 37 pts · June 16, 2026 · 52% 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