Tech
[Local LLM] DiffusionGemma
https://blog.google/innovation-and-ai/technology/developers-tools/diffusion-gemma-faster-text-generation/
在生成文本时,理论上可以比现在的版本快 4 倍。
本地运行步骤:
https://unsloth.ai/docs/models/diffusiongemma
目前 V2EX Chat 用的模型就是 gemma4:26b 。
https://edge.v2ex.com/chat
Read the full discussion on V2EX
This article was aggregated from V2EX. Click to join the conversation.
View on V2EX