The T4 16GB is a NVIDIA accelerator with 16 GB GDDR6 and about 320 GB/s peak memory bandwidth. AI Hashrate estimates local LLM decode (batch 1) at 8K context: fit counts weights + KV cache + 1 GB runtime overhead — not weights alone. At Q4, about 25 curated models fit fully on this card; at FP16, about 10 fit. Top Q4 speeds: Qwen3-0.6B ≈ 254.5 tok/s (estimated, fits); gemma-3-1b-it ≈ 203.6 tok/s (estimated, fits); Llama-3.2-1B-Instruct ≈ 169.7 tok/s (estimated, fits); Qwen3-1.7B ≈ 101.8 tok/s (estimated, fits); Llama-3.2-3B-Instruct ≈ 63.6 tok/s (estimated, fits). Relative ranking is more reliable than absolute tok/s. See methodology for the bandwidth formula and measured-anchor policy. Methodology.