RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can WeVisOne VL 2B run on the A100 40GB?

Yes. At 8K context the best fit is F16, using about 5.4 GB of the 38.0 GB usable on the A100 40GB. Estimated speed ceiling: ~382 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K) •1.9 GB Fits2.4 GB Fits5.0 GB Fits15.5 GB Fits1764
3-bit (Q3_K_M) •2.1 GB Fits2.6 GB Fits5.2 GB Fits15.7 GB Fits1446
4-bit (Q4_K_M) •2.3 GB Fits2.8 GB Fits5.4 GB Fits15.9 GB Fits1211
5-bit (Q5_K_M) •2.5 GB Fits2.9 GB Fits5.6 GB Fits16.1 GB Fits1055
6-bit (Q6_K) •2.7 GB Fits3.1 GB Fits5.8 GB Fits16.3 GB Fits928
8-bit (Q8_0) •3.1 GB Fits3.6 GB Fits6.2 GB Fits16.7 GB Fits717
16-bit (F16/BF16) •4.9 GB Fits5.4 GB Fits8.0 GB Fits18.5 GB Fits382

• real GGUF file size from mradermacher/WeVisOne-VL-2B-GGUF. Speed is a bandwidth ceiling (1555 GB/s), not a benchmark. Methodology.

More

WeVisOne VL 2B on every GPU and Mac · Every model that runs on the A100 40GB · Other models that fit 48 GB VRAM · Try other settings in the calculator

Data: Hugging Face Hub (tencent/WeVisOne-VL-2B), NVIDIA specs. Data as of 2026-11-17.