RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can falcon 7b instruct run on the RTX 3080 10GB?

Yes. At 8K context the best fit is Q2_K, using about 8.4 GB of the 9.5 GB usable on the RTX 3080 10GB. Estimated speed ceiling: ~206 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K) •6.2 GB Fits8.4 GB Fits21.7 GB No75.0 GB No206
3-bit (Q3_K_M) •6.4 GB Fits8.7 GB Tight22.0 GB No75.2 GB No191
4-bit (Q4_K_M) •7.2 GB Fits9.4 GB Tight22.7 GB No76.0 GB No159
5-bit (Q5_K_M) •7.9 GB Fits10.1 GB No23.4 GB No76.7 GB No—
6-bit (Q6_K) •9.0 GB Tight11.2 GB No24.5 GB No77.8 GB No—
8-bit (Q8_0) •9.6 GB No11.8 GB No25.1 GB No78.4 GB No—
16-bit (F16/BF16)16.2 GB No18.4 GB No31.7 GB No85.0 GB No—

• real GGUF file size from QuantFactory/falcon-7b-instruct-GGUF. Speed is a bandwidth ceiling (760 GB/s), not a benchmark. Methodology.

More

falcon 7b instruct on every GPU and Mac · Every model that runs on the RTX 3080 10GB · Other models that fit 12 GB VRAM · Try other settings in the calculator

Data: Hugging Face Hub (tiiuae/falcon-7b-instruct), NVIDIA specs. Data as of 2026-11-17.