RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can Llama 3.2 3B run on the RTX PRO 6000 Blackwell?

Yes. At 8K context the best fit is F16, using about 7.5 GB of the 91.2 GB usable on the RTX PRO 6000 Blackwell. Estimated speed ceiling: ~279 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K) •2.5 GB Fits2.9 GB Fits5.5 GB Fits16.0 GB Fits1200
3-bit (Q3_K_M) •2.8 GB Fits3.2 GB Fits5.9 GB Fits16.4 GB Fits965
4-bit (Q4_K_M) •3.2 GB Fits3.6 GB Fits6.2 GB Fits16.7 GB Fits800
5-bit (Q5_K_M) •3.5 GB Fits3.9 GB Fits6.6 GB Fits17.1 GB Fits691
6-bit (Q6_K) •3.8 GB Fits4.3 GB Fits6.9 GB Fits17.4 GB Fits604
8-bit (Q8_0) •4.7 GB Fits5.1 GB Fits7.7 GB Fits18.2 GB Fits467
16-bit (F16/BF16)7.1 GB Fits7.5 GB Fits10.1 GB Fits20.6 GB Fits279

• real GGUF file size from QuantFactory/OneLLM-Doey-V1-Llama-3.2-3B-GGUF. Speed is a bandwidth ceiling (1792 GB/s), not a benchmark. Methodology.

More

Llama 3.2 3B on every GPU and Mac · Every model that runs on the RTX PRO 6000 Blackwell · Other models that fit 64 GB VRAM · Try other settings in the calculator

Data: Hugging Face Hub (meta-llama/Llama-3.2-3B), NVIDIA specs. Data as of 2026-11-17.