GreenGames
- Karma
- 247
- Created
- 5 years ago
Recent Submissions
- 1. ▲ AMD Lucebox Beats Nvidia DGX Spark by 3.63x on DeepSeek V4 Flash (lucebox.com)
- 2. ▲ DeepSeek V4 Flash, up to 32 tok/s on AMD Ryzen AI MAX+ 395 (lucebox.com)
- 3. ▲ Laguna XS 2.1 33B on a RTX 3090: 296 tok/s peak, 152 tok/s at 256K context (lucebox.com)
- 4. ▲ 256K context with 72MiB of KV cache on the GPU (github.com)
- 5. ▲ A 35B MoE on a 16 GB GPU, without the offload tax (lucebox.com)
- 6. ▲ PFlash: 10x prefill speedup over llama.cpp at 128K on a RTX 3090 (github.com)
- 7. ▲ We got 207 tok/s with Qwen3.5-27B on an RTX 3090 (github.com)
- 8. ▲ Show HN: OS Megakernel that match M5 Max Tok/w at 2x the Throughput on RTX 3090 (github.com)
- 9. ▲ Cua (YC X25) is hiring an engineer (ycombinator.com)
- 10. ▲ App-Use, Control Individual Applications with CUA Agents (trycua.com)