GPU × use-case guide · Embeddings

Is the RTX 4090 a good GPU for embeddings?

The RTX 4090 is a ada NVIDIA GPU with 24 GB GDDR6X (1008 GB/s), 165 TFLOPS BF16 / 330 TFLOPS FP8, and a 450 W TDP. Embeddings workloads care most about maximum batch throughput on small encoder models — pure tokens-per-dollar. Here's how the RTX 4090 measures up.

What models fit on a single RTX 4090?

Weights only, reserving ~25% of the 24 GB for KV cache, activations and fragmentation. ✓ = fits on one card.

Largest single-card fit: Llama 3.1 8B at BF16, Qwen 2.5 14B at FP8, Gemma 2 27B at INT4. Bigger models need tensor-parallel across 4 cards.

RTX 4090 for embeddings, specifically

Embeddings is throughput-bound rather than VRAM-bound, so the RTX 4090's 1008 GB/s of bandwidth and 165 TFLOPS matter more than raw capacity. Because it runs offline, batch aggressively to push tokens-per-dollar down. Size it precisely on the calculator.

RTX 4090 pricing across providers

Verdict

At 24 GB, the RTX 4090 is a value card best suited to smaller embeddings models (up to Gemma 2 27B with INT4 quantisation). For larger models you'll want more VRAM or multi-GPU.