GPU Tokens Per Second Calculator: LLM Speed Estimator
Pick your GPU (or Mac) and a model — get an estimated tokens-per-second, then see how it stacks up against other hardware.
tune Your Setup
info How we calculate this
Speed: (Memory bandwidth × ~70% efficiency) ÷ active model weight size. This models the memory-bandwidth-bound nature of LLM inference.
Note: Real-world speed varies by engine (Ollama, llama.cpp, vLLM, MLX), driver version, and system load. Treat this as a planning estimate, not a guarantee.
Select your hardware and a model on the left to estimate speed.
Want it faster? RTX 4090 runs this ~2x quicker.
Get free local-AI deal alerts
Join our free list for the best deals on laptops, GPUs and Macs for running AI locally.
- ✓ Black Friday & Cyber Monday deals on laptops, GPUs and Macs for running AI locally
- ✓ No spam. Unsubscribe in one click.
We only use your email for TheAITechPulse emails. Privacy policy · About us · Contact