Hacker Newsalexfank
Show HN: llmrun – Find Which Open LLMs Fit Your GPU and How They Perform
Original title:Show HN: llmrun – which open LLMs run on your GPU, and how good they are
Open Source64
Sizing open-source language models for local hardware typically involves tedious calculations around VRAM capacity and quantization tradeoffs. llmrun (llmrun.dev) provides a targeted directory that matches specific GPU specifications against runnable open weights, paired with baseline performance and quality metrics. It gives local inference practitioners a practical reference to evaluate hardware compatibility without trial-and-error setup overhead.
Why it's worth reading
It cuts down the trial-and-error of running local LLMs by directly mapping GPU hardware constraints to compatible open-source models and benchmarks.
Tags
LLMOpenSourceGPULocalInferenceDevToolsHardware