RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can Llama 2 7b hf run on the RTX 3090?

Yes. At 8K context the best fit is F16, using about 17.0 GB of the 22.8 GB usable on the RTX 3090. Estimated speed ceiling: ~69 tokens/sec.

Memory by quant and context

Quant4K ctxMax tok/s (est., 8K)
2-bit (Q2_K) •4.8 GB Fits370
3-bit (Q3_K_M) •5.5 GB Fits284
4-bit (Q4_K_M) •6.3 GB Fits229
5-bit (Q5_K_M) •6.9 GB Fits196
6-bit (Q6_K) •7.6 GB Fits169
8-bit (Q8_0)9.1 GB Fits131
16-bit (F16/BF16)15.0 GB Fits69

• real GGUF file size from mradermacher/Llama-2-7b-hf-i1-GGUF. Speed is a bandwidth ceiling (936 GB/s), not a benchmark. Methodology.

More

Llama 2 7b hf on every GPU and Mac · Every model that runs on the RTX 3090 · Other models that fit 24 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.