Qwen3.8 125B (6B active) Flash-Next
on M1 Max 64GB · Espetero
Summary
User reports Qwen3.8 Flash-Next 125B at ~18 tok/s on an M1 Max 64GB with the Espetero server, an inference server for Apple silicon written in C++20 and Metal.
Setup streams experts from the SSD; the server loads MLX and GGUF files and serves OpenAI, Anthropic and Ollama APIs.
DeepSeek-V4.1-Flash 552B runs at ~10 tok/s on a 128 GB Mac Studio, described as experimental.