local intelligence

can it run

Can the Tesla P4 (8GB, used) run SDXL SDXL base?

STRETCH

Only with compromises. 8GB is below the 9GB working set — expect a lower quant, offloading, or heavy swap. Possible, not pleasant.

~7.8–14 tok/s

weights 6.9GB + KV cache 2GB at 4k context vs ~8GB usable → offload-partial. 8.9 GB vs 8 GB usable — partial CPU offload, expect large speed loss

computed roofline: 192.3 GB/s × 0.28–0.50 efficiency window / 6.9GB (Q4_K_M) — bands, never points.

explore the full catalog90 machines indexed · live prices · what each one can run

Specs

model file6.9GB (GGUF Q4_K_M)
minimum memory9GB working set
this machine8GB GDDR5, 192 GB/s
paramsSDXL base
licenseopenrail++
price$100

Run it

model files: hugging face ↗

easy run: no stock runtime yet

Alternatives

Tesla M60 (16GB, used) — cheapest machine that runs it ($35)

every model the Tesla P4 (8GB, used) can run — full list

tesla-p100-16gb — the next step up from this machine's GPU

Buy

eBay (used) ↗ · Amazon ↗

2026-09-20 · ← all models on the Tesla P4 (8GB, used) · ← full hardware catalog · prices verified at source, may drift