RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can Kimi VL A3B Instruct run on the H100 SXM?

Yes. At 8K context the best fit is F16, using about 31.5 GB of the 76.0 GB usable on the H100 SXM. Estimated speed ceiling: ~558 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K) •7.0 GB Fits7.1 GB Fits7.8 GB Fits10.6 GB Fits2784
3-bit (Q3_K_M) •8.6 GB Fits8.7 GB Fits9.4 GB Fits12.2 GB Fits2210
4-bit (Q4_K_M) •10.6 GB Fits10.8 GB Fits11.5 GB Fits14.3 GB Fits1738
5-bit (Q5_K_M) •12.0 GB Fits12.2 GB Fits12.9 GB Fits15.7 GB Fits1522
6-bit (Q6_K) •14.1 GB Fits14.2 GB Fits15.0 GB Fits17.8 GB Fits1283
8-bit (Q8_0) •16.6 GB Fits16.8 GB Fits17.5 GB Fits20.3 GB Fits1079
16-bit (F16/BF16)31.4 GB Fits31.5 GB Fits32.2 GB Fits35.1 GB Fits558

• real GGUF file size from mradermacher/Kimi-VL-A3B-Instruct-GGUF. Speed is a bandwidth ceiling (3350 GB/s), not a benchmark. Methodology.

More

Kimi VL A3B Instruct on every GPU and Mac · Every model that runs on the H100 SXM · Other models that fit 64 GB VRAM · Try other settings in the calculator

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