Tech
[问与答] Nvidia 128G 的那个小盒子用哪个模型好?
试了最新出的 Qwen3.8-27B ,吐字很慢,4token/s 。
试了 Qwen3.6-35B-A3B ,质量感觉不行,幻觉有些严重。
Read the full discussion on V2EX
This article was aggregated from V2EX. Click to join the conversation.
View on V2EX