llama

Show HN: LoRA over GGUF – Train Qwen3.8-Flash-Next in 40G VRAMOct 10, 2026 · Other → Underdog Saluki: Qwen3.8-27B in under 8GB with tool calling intactOct 9, 2026 · Other → Show HN: Superwhisper S1 mini – Text and tone normalizer for speech-to-textOct 8, 2026 · Research → AI Development on Windows: From PyTorch and Llama.cpp to Windows MLOct 7, 2026 · PolicyChange → How Cloudflare addressed a cross-tenant data exposure vulnerability in ContainersSep 22, 2026 · SecurityIncident →