RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can Kimi VL A3B Thinking 2506 run on the A100 80GB?

Yes. At 8K context the best fit is F16, using about 60.4 GB of the 76.0 GB usable on the A100 80GB. Estimated speed ceiling: ~175 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K)6.6 GB Fits6.7 GB Fits7.4 GB Fits10.2 GB Fits1812
3-bit (Q3_K_M)8.3 GB Fits8.4 GB Fits9.1 GB Fits12.0 GB Fits1391
4-bit (Q4_K_M) •10.6 GB Fits10.8 GB Fits11.5 GB Fits14.3 GB Fits1058
5-bit (Q5_K_M)11.7 GB Fits11.8 GB Fits12.5 GB Fits15.4 GB Fits954
6-bit (Q6_K)13.4 GB Fits13.5 GB Fits14.2 GB Fits17.0 GB Fits829
8-bit (Q8_0) •16.6 GB Fits16.8 GB Fits17.5 GB Fits20.3 GB Fits657
16-bit (F16/BF16) •60.3 GB Fits60.4 GB Fits61.1 GB Fits64.0 GB Fits175

• real GGUF file size from ggml-org/Kimi-VL-A3B-Thinking-2506-GGUF. Speed is a bandwidth ceiling (2039 GB/s), not a benchmark. Methodology.

More

Kimi VL A3B Thinking 2506 on every GPU and Mac · Every model that runs on the A100 80GB · Other models that fit 64 GB VRAM · Try other settings in the calculator

Data: Hugging Face Hub (moonshotai/Kimi-VL-A3B-Thinking-2506), NVIDIA specs. Data as of 2026-11-17.