🤩牛逼！Qwen3.8-Flash-Next 性能再次突破，Mac 提速 31%，Strix Halo Windows 翻倍，低显存几乎 3 倍！
This is a AI post classified by AGK Intelligence as Open & local models (a tool drop), kept by the AI Radar because it carries real work, not commentary.
🤩牛逼！Qwen3.8-Flash-Next 性能再次突破，Mac 提速 31%，Strix Halo Windows 翻倍，低显存几乎 3 倍！ 本地跑 Qwen3.8-Flash-Next 的神器 Strata 0.2.12 再次进化，专为消费级硬件优化： 🔹全新训练的 DFlash2 drafter（针对 Strix Halo + Mac 深度调优） 🔹Mac tokens/s 最高提升 31%（M5 Max 实测答案速度明显拉升） 🔹Strix Halo：Windows 上最高 2.1× 更快，Linux 接近 3× 🔹低显存/低内存配置（如 12GB 卡）长 Prompt 最高 3.3× 提速 🔹20+ Tool Call 修复，工具调用稳定性大幅提升 Mac 党、AMD Strix Halo 用户、12GB 显卡玩家直接起飞。一键安装，本地 OpenAI/Anthropic API 兼容，隐私拉满。 立即更新体验： GitHub Releases：https://github.com/Niko1221/Strata/releases/tag/v0.2.12 项目主页：https://github.com/Niko1221/Strata #Strata #本地大模型 #MacAI #WindowsAI #本地AI #LLM #Qwen #消费级AI #开
Posted by SuSu_酥酥👅 (27.1k followers) 7 h ago · 38 likes · 5k views · view the original post on X. Kept by the AI Radar as Open & local models. Tools mentioned: strata, qwen3.8-flash-next-gguf, unsloth.ai.
More AI work like this
- 💥细节感拉满！Qwen 4.0 蜜蜂向日葵测试炸了！ — @NFT_Chen
- @TheZachMueller — @TheZachMueller
- Here DSv4.1 Flash recipe by @christopherowen in action! — @ivanfioravanti
- Qwen Qoduck 花了 2 个小时生成的美国白宫 3D 建模 — @leo114119
- HyperFlow H3 Flash has passed 15,000 downloads on @huggingface in under 24 hours. — @video_rebirth
- Every lab should ship its own 4bit weights. — @plotarmordev
- Qwen 4 Unknown Preview bee on a sunflower. — @loktar00
- Meet DroidSenior-7B-v3-i1-GGUF: a 7B model fine-tuned for Android devs. Built on Qwen2… — @HuggingModels
Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 65.2k posts from 5k X accounts over the last 14 days, 10.5k tools, 19 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-07 16:40 UTC. Full method.