local intelligence

can it run

Can the Tesla P4 (8GB, used) run gemma3 12B?

NO

No. 8GB of memory can't hold the 11GB working set this model needs. A smaller quant or a bigger machine is required.

~6.6–12 tok/s

weights 8.1GB + KV cache 1.5GB at 4k context vs ~8GB usable → offload-partial. 9.6 GB vs 8 GB usable — partial CPU offload, expect large speed loss

computed roofline: 192.3 GB/s × 0.28–0.50 efficiency window / 8.1GB (Q4_K_M) — bands, never points.

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

Specs

model file8.1GB (GGUF Q4_K_M)
minimum memory11GB working set
this machine8GB GDDR5, 192 GB/s
params12B
licensegemma
price$100

Run it

model files: hugging face ↗

easy run: ollama pull gemma3:12b

runs with: ollama · llama.cpp · koboldcpp · lm studio

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