smolmaxxing: making LLMs work on small and old devices
mrashad74 · hn · 2026-11-12
An open-source project, smolmaxxing, focused on getting LLMs to run on small and old devices, exploring local inference paths for low-end hardware. Useful for developers interested in edge deployment and squeezing model inference out of legacy machines.
More from Infra
- Accord GPU open beta queues ComfyUI, Blender, Ollama to stop VRAM fights — MrAddams_LibraLogic · 2026-11-13
- Ex-Nvidia CUDA engineer: 'CUDA is not the moat — Nvidia's only moat is its people' — AlpinDale · 2026-11-13
- AMD expands PsiQuantum partnership with planned equity investment in photonic quantum computing — sven_ai · 2026-11-13
- Nvidia downgrades hit seven as analysts say depths 'not fully probed' — SumitGup · 2026-11-13
- AMD Advancing AI World Tour Japan set for Dec 1 in Tokyo with KDDI, Microsoft, AMD execs — DavidBennett__ · 2026-11-13
- WSJ: Jensen Huang called CFO a 'deer in the headlights' over AI funding plan woes — GaryMarcus · 2026-11-13