1Mercury 2 on PinchBench: Diffusion LLM benchmarked on real OpenClaw agent tasks (opens in new tab)(inceptionlabs.ai)2volodia21h ago0
2Mercury 2: Best-in-class speed-optimized intelligence at 1,200 tok/SEC (opens in new tab)(twitter.com)1volodia29d ago0
3Finetuning 3-Bit LLMs on Consumer GPUs by Integrating with Modular Quantizers (opens in new tab)(arxiv.org)2volodia2y ago0
4LLMTune: 4-Bit finetuning of 65B LLAMA models on a single consumer GPU (opens in new tab)(github.com)3volodia2y ago0
6Don't have a $5k MacBook to run LLAMA65B? MiniLLM runs LLMs on GPUs in <500 LOC (opens in new tab)(github.com)3volodia3y ago2
