GPU
RTX 4060 Ti 16GB
Best price-to-VRAM ratio for 8B-13B models at full precision quantization.
42.7 Tokens/sec (Llama 3 8B, Q8)
Verified Full benchmark writeup pending — placeholder entry for homepage layout.
GPU
Best price-to-VRAM ratio for 8B-13B models at full precision quantization.
Full benchmark writeup pending — placeholder entry for homepage layout.