Qwen3.8-Flash-Next on MLX-serve, 1m context is released!

Article automatically generated from technical news.

Hi, I'm the co-creator of this Qwen3.8-Flash-Next engine support in MLX-serve. I've been tuning this one to run both fast, efficient and correct up 1m context using kv cache 8 bits in M5 Max 128GB. Qwen is working well at very long context as showed in the video (a snapshot at ~760k context), I let it build MLX Serve Monitor plugin that you've seen on the right side of Opencode2's app. The generation sustain through 1m context at around 40 tok/s on prose and 75 tok/s on coding.