发布节奏
最近 12 周每周中位浏览
最近 12 周发布时间
颜色 = 中位浏览爆款 vs 日常
爆款 = 浏览前 10%| 指标 | 爆款 | 日常 |
|---|---|---|
| 帖子 | 1 | 8 |
| 带媒体 | 0% | 25% |
| 回复 | 0% | 0% |
| 平均字数 | 306 | 164 |
| 中位浏览 | 11.6万 | 2.9万 |
打法建议
只陈述相关性- 互动最好的时段是 01:00 前后（北京时间），中位浏览 1.1万。
- 一周里 周二 的中位浏览最高。
- 形式上 纯文字 的中位浏览更高（2.1万 vs 4.3万）。
- 爆款里带媒体占 0%、回复占 0%；日常分别是 25%、0%。
- 当前节奏约 0.3 条/天，日均浏览 4.7万。
内容结构
按本站分析的分类（近 120 天）- 产品1
形式与语言
帖子占比- 纯文字7
- 图片2
回复占比 0% · 引用 44.4% · 带媒体 22.2%
互动最高的帖子
按浏览排序- 1
Decision models in llama.cpp are now available The `/v1/systemone` endpoint is available in the latest llama builds. Use it to do Jev-style inference locally, efficiently and privately. Multiple open models are supported with more to come. https://huggingface.co/blog/ggml-org/decision-models-in-llamacpp
- 2
The new v0.6.0 release packs a lot of good stuff: - Clef support (text + vision) - High-quality support for Qwen3.8-Flash-Next - Massive performance improvement with Metal - New `llama_batch_ext` API Also the website got a nice refresh: https://llama.app
- 3
Run GGUF models directly with transformers. This work brings ggml's Metal kernels to the transformers ecosystem, increasing compatibility and performance. More info below
- 4
If you are using Qwen3.8-27B + MTP, make sure to upgrade to DFlash for extra speed: llama serve -hf ggml-org/Qwen3.8-27B-GGUF --spec-type draft-dflash --spec-draft-n-max 7 Requires the latest llama.cpp v0.6.0
- 5
It is very cool to see llama.cpp on the big stage in todays Windows event! The software and hardware stacks are finally coming together. Our community has put a lot of hard work in the past years and it shows. Looking forward to more users embracing local AI.
- 6
Day-0 support for EmbeddingGemma 2 in llama.cpp https://huggingface.co/ggml-org/embeddinggemma-2-GGUF
- 7
llama.cpp can distribute inference on heterogeneous devices through the ggml RPC backend It's an advanced setting but I think with time we'll make it more accessible to regular users.
- 8
（无文字）
- 9
llama.cpp v0.7.0, 128GB Mac/Spark: llama serve -hf ggml-org/Qwen3.8-Flash-Next-GGUF:IQ4_NL --spec-type draft-mtp --lazy-mode on
点赞、转发、浏览是采集那一刻的快照，不是帖子最终数据；时间为北京时间。KPI 卡片里的同比只在账号有 8 周以上数据时显示， 否则只看近 4 周。“打法建议”只说明数据里的相关性，不代表因果。