▲ local intelligence

can it run

Can the NVIDIA L4 run FLUX schnell fp8?

FULL

19.0 GB needed of 24 GB usable — headroom for context

24GB · Ampere · model file 17GB · schnell fp8

~9.7–16 tok/s

computed roofline: 300 GB/s × 0.55–0.88 efficiency window / 17.0GB (Q4_K_M) — bands, never points.

Run FLUX schnell fp8 on instead

→ Tesla V100 32GB (used) — cheapest catalog machine that runs FLUX schnell fp8 fully ($700)

→ RTX 4090 (24GB, used) — upgrade path machine

→ every model the NVIDIA L4 can run — full list

→explore the full catalog91 machines indexed · live prices · what each one can run
2026-10-01 · ← all models on the NVIDIA L4 · fit = weights + 4k KV vs usable memory