RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can DeepSeek V2 Lite Chat run on the RTX 5090?

Yes. At 8K context the best fit is Q8_0, using about 16.4 GB of the 30.4 GB usable on the RTX 5090. Estimated speed ceiling: ~633 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K) •6.7 GB Fits6.8 GB Fits7.5 GB Fits10.4 GB Fits1645
3-bit (Q3_K_M) •8.3 GB Fits8.4 GB Fits9.1 GB Fits12.0 GB Fits1301
4-bit (Q4_K_M) •10.4 GB Fits10.5 GB Fits11.2 GB Fits14.0 GB Fits1020
5-bit (Q5_K_M) •11.8 GB Fits11.9 GB Fits12.6 GB Fits15.4 GB Fits892
6-bit (Q6_K) •13.8 GB Fits13.9 GB Fits14.6 GB Fits17.5 GB Fits752
8-bit (Q8_0) •16.3 GB Fits16.4 GB Fits17.1 GB Fits19.9 GB Fits633
16-bit (F16/BF16)30.0 GB Tight30.1 GB Tight30.8 GB No33.6 GB No337

• real GGUF file size from mradermacher/DeepSeek-V2-Lite-Chat-GGUF. Speed is a bandwidth ceiling (1792 GB/s), not a benchmark. Methodology.

More

DeepSeek V2 Lite Chat 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 (deepseek-ai/DeepSeek-V2-Lite-Chat), NVIDIA specs. Data as of 2026-11-17.