RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can Qwen3 VL 8B Instruct run on the H100 PCIe?

Yes. At 8K context the best fit is F16, using about 17.1 GB of the 76.0 GB usable on the H100 PCIe. Estimated speed ceiling: ~122 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K)4.3 GB Fits4.9 GB Fits8.3 GB Fits21.8 GB Fits608
3-bit (Q3_K_M)5.2 GB Fits5.8 GB Fits9.2 GB Fits22.7 GB Fits467
4-bit (Q4_K_M) •5.9 GB Fits6.5 GB Fits9.9 GB Fits23.4 GB Fits398
5-bit (Q5_K_M)7.1 GB Fits7.6 GB Fits11.0 GB Fits24.5 GB Fits320
6-bit (Q6_K)7.9 GB Fits8.5 GB Fits11.9 GB Fits25.4 GB Fits278
8-bit (Q8_0) •9.4 GB Fits9.9 GB Fits13.3 GB Fits26.8 GB Fits230
16-bit (F16/BF16) •16.5 GB Fits17.1 GB Fits20.5 GB Fits34.0 GB Fits122

• real GGUF file size from Qwen/Qwen3-VL-8B-Instruct-GGUF. Speed is a bandwidth ceiling (2000 GB/s), not a benchmark. Methodology.

More

Qwen3 VL 8B Instruct on every GPU and Mac · Every model that runs on the H100 PCIe · Other models that fit 64 GB VRAM · Try other settings in the calculator

Data: Hugging Face Hub (Qwen/Qwen3-VL-8B-Instruct), NVIDIA specs. Data as of 2026-11-17.