RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can Llama 2 7b hf run on the RTX 5090?

Yes. At 8K context the best fit is F16, using about 17.0 GB of the 30.4 GB usable on the RTX 5090. Estimated speed ceiling: ~133 tokens/sec.

Memory by quant and context

Quant4K ctxMax tok/s (est., 8K)
2-bit (Q2_K) •4.8 GB Fits707
3-bit (Q3_K_M) •5.5 GB Fits543
4-bit (Q4_K_M) •6.3 GB Fits439
5-bit (Q5_K_M) •6.9 GB Fits375
6-bit (Q6_K) •7.6 GB Fits324
8-bit (Q8_0)9.1 GB Fits250
16-bit (F16/BF16)15.0 GB Fits133

• real GGUF file size from mradermacher/Llama-2-7b-hf-i1-GGUF. Speed is a bandwidth ceiling (1792 GB/s), not a benchmark. Methodology.

More

Llama 2 7b hf on every GPU and Mac · Every model that runs on the RTX 5090 · Other models that fit 32 GB VRAM · Try other settings in the calculator

Data: Hugging Face Hub (NousResearch/Llama-2-7b-hf), NVIDIA specs. Data as of 2026-11-17.