Show HN: Run Qwen3-Next-80B on 8GB GPU at 1tok/2s throughput(github.com)97 points by anuarsh 1 year ago | 10 comments
PhaseLLM: Standardized Chat LLM API (Cohere, Claude, GPT) + Evaluation Framework(github.com)71 points by cl42 3 years ago | 3 comments
EM-LLM: Human-Inspired Episodic Memory for Infinite Context LLMs(github.com)95 points by jbotz 1 year ago | 10 comments
Show HN: ZQDGR a Script Runner for Golang(github.com)13 points by zoezoezoezoe 1 year ago | 4 comments