Mellum by JetBrains

你认为最终有多大比例的实际开发者任务可以由像Mellum这样的专用模型处理，而完全不需要前沿模型？

以低延迟为先的模型被低估了。我运营着AI语音智能体，在实时通话中，低延迟不是锦上添花，而是整个用户体验的核心——2秒的停顿会让来电者觉得系统坏了，这种感觉在IDE里是绝对不会出现的。对于狭窄、边界清晰的任务，我每次都选择“快且够用”，而不是“慢而惊艳”。你会考虑把Mellum用于实时/语音场景吗？还是说它完全瞄准了编码循环？

我们需要看到更多这样的东西，才能摆脱对基于云的模型的依赖。

Really like the latency-first direction here. Not every AI workflow needs a frontier model — especially for completion, routing, classification, and small sub-agent tasks where speed and cost matter a lot.

Would love to know how Mellum performs in local/self-hosted setups compared to cloud inference.

Fast, focused models make a lot of sense for coding. I’d rather get a useful completion instantly than wait for a huge model to overthink it.

它与Qwen 3.6和Gemma 4模型相比如何？只看到旧模型让人失望，感觉有误导性。