Benchmarking Archives

DwarfStar Strikes Again: Mac Studio M3 Ultra runs Qwen 3.8 Flash Next Q4 at 810 t/s Prefill

Qwen 3.8 Flash Next Q4 on a 96 GB M3 Ultra Mac Studio: 810 t/s prefill flat to 200k context, 53–61 t/s decode, 89.2 GB resident — and the wired limit to raise.

Benchmarking, ds4, Engram, LLM Inference, Local AI, Mac Studio, Quantization, Qwen

Speed versus smarts: choosing the right local model size — featured banner

AMD Distributed Inference

Speed vs. Smarts: When Bigger Models Win for Local AI Coding

At AIFinitee, we've spent months chasing tokens per second. Our two-node AMD Ryzen AI MAX cluster hits 17-20 tok/s with MiniMax-M2. Our Linux-vs-Windows benchmarks showed how your OS quietly taxes…

Benchmarking, LLM Inference, Local AI, Strix Halo

Linux vs Windows for LLM inference — featured banner

AMD Distributed Inference

Linux vs Windows for LLM Inference: More Tokens/Second on Linux

Same GPU, different OS = different performance. See why Linux delivers 5-30% more tokens/sec than Windows across NVIDIA, AMD, and Intel GPUs.

Benchmarking, Linux, LLM Inference, Local AI, Strix Halo

AMD Distributed Inference MiniMax

Strix Halo Cluster

One of the beliefs we hold at AIfinitee is that LLMs will only get bigger. Bigger LLMs will mean more memory for usage in either cloud compute or local compute.…

Benchmarking, Cluster Computing, LLM Inference, Local AI, Strix Halo