RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can Qwen3 8B run on the 2x RTX 4090?

Yes. At 8K context the best fit is F16, using about 17.1 GB of the 45.6 GB usable on the 2x RTX 4090. Estimated speed ceiling: ~62 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctx32K ctxMax tok/s (est., 8K)
2-bit (Q2_K)4.1 GB Fits4.7 GB Fits8.1 GB Fits328
3-bit (Q3_K_M)5.0 GB Fits5.5 GB Fits8.9 GB Fits252
4-bit (Q4_K_M) •5.9 GB Fits6.5 GB Fits9.9 GB Fits200
5-bit (Q5_K_M) •6.7 GB Fits7.3 GB Fits10.6 GB Fits172
6-bit (Q6_K) •7.5 GB Fits8.1 GB Fits11.5 GB Fits150
8-bit (Q8_0) •9.4 GB Fits9.9 GB Fits13.3 GB Fits116
16-bit (F16/BF16)16.5 GB Fits17.1 GB Fits20.4 GB Fits62

• real GGUF file size from Qwen/Qwen3-8B-GGUF. Speed is a bandwidth ceiling (1008 GB/s), not a benchmark. Methodology.

More

Qwen3 8B on every GPU and Mac · Every model that runs on the 2x RTX 4090 · Try other settings in the calculator

Data: Hugging Face Hub (Qwen/Qwen3-8B), NVIDIA specs. Data as of 2026-11-17.