GreenGames
- Karma
- 251
- Created
- 6 years ago
Recent Submissions
- 1. ▲ $5,999 Ryzen AI MAX+ 395 and Radeon R9700 workstation (videocardz.com)
- 2. ▲ We got DSV4 Flash 0731 to 32.7 tok/s on AMD Strix Halo (lucebox.com)
- 3. ▲ AMD Lucebox Beats Nvidia DGX Spark by 3.63x on DeepSeek V4 Flash (lucebox.com)
- 4. ▲ DeepSeek V4 Flash, up to 32 tok/s on AMD Ryzen AI MAX+ 395 (lucebox.com)
- 5. ▲ Laguna XS 2.1 33B on a RTX 3090: 296 tok/s peak, 152 tok/s at 256K context (lucebox.com)
- 6. ▲ 256K context with 72MiB of KV cache on the GPU (github.com)
- 7. ▲ A 35B MoE on a 16 GB GPU, without the offload tax (lucebox.com)
- 8. ▲ PFlash: 10x prefill speedup over llama.cpp at 128K on a RTX 3090 (github.com)
- 9. ▲ We got 207 tok/s with Qwen3.5-27B on an RTX 3090 (github.com)
- 10. ▲ Show HN: OS Megakernel that match M5 Max Tok/w at 2x the Throughput on RTX 3090 (github.com)