Qwen3 30B A3B Hits 13 token/s on 4xRaspberry Pi 5
https://github.com/b4rtaz/distributed-llama/discussions/255
#HackerNews #Qwen3 #A3B #RaspberryPi #TokenSpeed #DistributedLLama
[v0.16.0] Qwen3 30B A3B Q40 on 4 x Raspberry Pi 5 8GB · b4rtaz distributed-llama · Discussion #255
qwen3_30b.mov Setup Device: 4 x Raspberry Pi 5 8GB Distributed Llama version: 0.16.0 Model: qwen3_30b_a3b_q40 Benchmark Evaluation Prediction 4 x Raspberry Pi 5 8GB 14.33 tok/s 13.04 tok/s b4rtaz@r...