GPU × use-case guide · Long context

Is the T4 a good GPU for long context?

The T4 is a turing NVIDIA GPU with 16 GB GDDR6 (300 GB/s), 65 TFLOPS BF16 / 65 TFLOPS FP8, and a 70 W TDP. Long context workloads care most about raw VRAM for the KV cache — context length, not weights, is what fills the card. Here's how the T4 measures up.

What models fit on a single T4?

Weights only, reserving ~25% of the 16 GB for KV cache, activations and fragmentation. ✓ = fits on one card.

Largest single-card fit: none (needs multi-GPU) at BF16, Llama 3.1 8B at FP8, Qwen 2.5 14B at INT4. Bigger models need tensor-parallel across 8 cards.

T4 for long context, specifically

Long context is context-heavy, so the KV cache — not the weights — is what fills the 16 GB. On the T4 you'll trade context length against batch size: long prompts mean fewer concurrent requests. Because it runs offline, batch aggressively to push tokens-per-dollar down. Size it precisely on the calculator.

T4 pricing across providers

Verdict

At 16 GB, the T4 is a value card best suited to smaller long context models (up to Qwen 2.5 14B with INT4 quantisation). For larger models you'll want more VRAM or multi-GPU.