AmSach
- Karma
- 15
- Created
- 1 year ago
About
Systems & ML engineer. Creator of MAPLE (Manifold-Activated Pruning of Latent Experts) - running Gemma 4 26B MoE on 6GB consumer GPUs at 45.4 TPS with 100% quality retention. GitHub: https://github.com/AmSach/maple amansachan92905@gmail.com contact meRecent Submissions
- 1. ▲ Show HN: DeepSeek-Coder-V2-Lite Under 5GB: 65 TPS 100% In-VRAM on 6GB GPU (huggingface.co)
- 2. ▲ Show HN: Maple – Run Gemma 4 26B on a 6GB Laptop GPU at 45 TPS (Sub-2-BPW) (amsach.github.io)
- 3. ▲ Show HN: Maple – Sub-2-BPW Moe Pruning to Run Gemma 4 26B at 45 TPS on a 6GB GPU (github.com)