OMG! If you have a Mac with 64GB, try Qwen3.8-Flash-Next-oQ4e-mtp with oMLX!

I'm genuinely shocked! I was able to run Qwen3.8-Flash-Next-oQ4e-mtp on M3Max 64GB with oMLX! Yes, there are other 3bit quants for 64GB Mac, but 4bit is the lowest quant I'd tolerate. I manually quantized the original model from the Qwen repo to OQ4E using oMLX, and it turned out to be about 4.72 BP

中文全文翻译正在补齐，可先查看下方英文原文。

I'm genuinely shocked! I was able to run Qwen3.8-Flash-Next-oQ4e-mtp on M3Max 64GB with oMLX! Yes, there are other 3bit quants for 64GB Mac, but 4bit is the lowest quant I'd tolerate. I manually quantized the original model from the Qwen repo to OQ4E using oMLX, and it turned out to be about 4.72 BP