Provider guide
Where to run Llama 3.2 3B Instruct
4 live offers tracked — output prices vary 6.7× between the cheapest and most expensive host, so the provider choice matters as much as the model choice.
FASTEST MEASURED
73 tok/s
measured throughput · $0.051 input / $0.34 output per million tokens
Novita AI$0.030 in/1M$0.050 out/1M—33K—9h agoOpenRouterCHEAPEST$0.050 in/1M$0.33 out/1M—131K—3h agoCloudflare Workers AI$0.051 in/1M$0.34 out/1M73 tok/s80K—3h agoParasailzero-retention$0.050 in/1M$0.33 out/1M61 tok/s131Kbf169h ago
Novita AIFull specs, hardware verdicts and benchmarks on theLlama 3.2 3B Instruct model page →