All GPUs

RTX 4080 SUPER

NVIDIA · Ada Lovelace · 16 GB · 2024

Can this card run it?

Yes — run Qwen3.8-Flash-Next at Q2_0.

Download 70 GB · needs 48 GB system RAM.

Download the NVIDIA · CUDA build.

Specifications

VRAM16 GB
Memory bandwidth736 GB/s
Reading speed2921 tok/s
Writing speed79.8 tok/s
Data sourceestimated

This card is not benchmarked yet. The speeds are estimated from memory bandwidth and will be replaced when we measure it.

See the full benchmark