self-hosted/ai
§01·model · /models

Llama 3.2 1B

llmactive
§02·GPUs that run this model
3 total
GPUVRAMSeriesBest speedMin VRAMWorksBenchmarks
RTX 5060 Ti16GB50192tokens/s16GB2check ↗
RTX 4060 Ti 16GB16GB40130tokens/s16GB1check ↗
RX 7900 XTX24GBamd106tokens/s24GB1check ↗