博主雷达 / @ollama
ollama
AI官方精选模型厂商官方@ollama
粉丝 18.6万关注 401最近同步 10/19 14:48雷达库已收录
在本地一键运行开源大模型的工具,官方账号。
去 X 主页粉丝趋势近 30 天
近 7 天
数据积累中
情报贡献参与 6 条已上架情报 · 首发 6 条
- 限免Ollama 上线 Reflection AI 首个开放权重模型 Beam 并限时免费10/17 18:20
- 新模型Ollama 上线 beam 模型页面并发布博客10/18 15:21
- 新模型NVIDIA Nemotron 3.5 Bolt上线Ollama10/16 16:21
- 新模型NVIDIA Nemotron 3.5 Super VL上线Ollama10/16 16:21
- API 变动Muse Spark Open扩展至Pro等套餐10/16 16:21
最近帖子最多 20 条
✈ DeepSeek-V4.1-Flash-1017 上线 Ollama 了!美国本土托管,零数据留存。 它在 agentic 任务上很强,同时每个任务的成本更低。 在 Ollama Cloud 上试试: ollama run deepseek-v4.1-flash:1017-cloud Claude Code: ollama launch claude --model deepseek-v4.1-flash:1017-cloud OpenCode: ollama launch opencode --model deepseek-v4.1-flash:1017-cloud
🚀 DeepSeek-V4.1-Flash-1017 is here! Stronger benchmark performance, faster task completion, and shorter outputs than the previous version—a Pareto improvement in performance and cost. Now live on our website, app, and API. 🛠️ Optimized for @DeepSeekHarness, Tencent CodeBuddy, WorkBuddy, and more. Upgrade to DeepSeek Harness v0.2.1-rc.1 or later for the best experience with the new model. 1/4
查看被引用的帖子正在努力让我们的美国主机上线。很快了!
🚀 DeepSeek-V4.1-Flash-1017 is here! Stronger benchmark performance, faster task completion, and shorter outputs than the previous version—a Pareto improvement in performance and cost. Now live on our website, app, and API. 🛠️ Optimized for @DeepSeekHarness, Tencent CodeBuddy, WorkBuddy, and more. Upgrade to DeepSeek Harness v0.2.1-rc.1 or later for the best experience with the new model. 1/4
查看被引用的帖子你好 🇰🇷 行李收拾好了。Ollama 要去首尔了 ✈️ 韩国是世界上最创新的 AI 市场之一,而且首尔有如此活跃的 Ollama 社区,我们早就想走这一趟了。终于要去了,真的很兴奋。 今年 11 月,我们会在当地见用户、客户和合作伙伴,了解我们如何在这个市场进一步成长。 我们在首尔期间还会和 @friendliai 合作。更多消息后续公布 👀
我们很兴奋能成为 @reflection_ai 首个开放权重模型的 day 0 合作伙伴!限时期间, Beam 在 Ollama 上免费使用!我们与 @reflection_ai 合作,该模型托管在美国,提供完整的 ZDR。 它拥有 1M token 的上下文窗口,专为软件工程、推理和长时间运行的智能体任务而设计。 在 Ollama 的 Cloud 上运行 Beam: ollama run beam Claude Code ollama launch claude --model beam:cloud Codex ollama launch codex --model beam:cloud OpenCode ollama launch opencode --model beam:cloud 限时免费使用。
Beam is now available across platforms, with open weights under the Apache 2.0 license - in collaboration with an ecosystem of 40+ partners. We're releasing: - Weights, tokenizer, and reference implementation - BF16, FP8 and NVFP4 weights and a DFlash2 drafter - The open source harness we built and trained Beam on: Mirror CLI Weights and model card on Hugging Face: huggingface.co/reflection
查看被引用的帖子Muse Spark Open 现已向 Pro、Max、按量付费和 Teams 套餐推出。
Muse Spark Open is now on Ollama. @Meta's open-weight model for coding and tool use, with a 1M-token context window. Run it on Ollama’s cloud: ollama run muse-spark-open:cloud Use with Claude Code: ollama launch claude muse-spark-open:cloud Now available to Max and Teams users, and rolling out to Pro users soon!
查看被引用的帖子看到 @AIatMeta 发布了目前美国最强的开放权重模型,太棒了! 这个模型很快就能在 Ollama 上用了。🫡
Today we’re releasing Muse Spark Open, the most capable US open-weight model to date. Built for coding and agentic work, it excels at long-horizon tasks, complex software engineering, and multi-step reasoning. Key Model Specs: → 816B total / 42B active parameters → 1M token context window → Natively multimodal across text, image, video, audio
查看被引用的帖子认识一下 Ollama 联合创始人兼 CEO @jmorgan,他聊了聊企业在采用开放模型方面的情况。 观看这期节目 👇
ollama run lfm2.5:24b ollama.com/library/lfm2.5:24b
Today we release 𝙻𝙵𝙼𝟸.𝟻-𝟸𝟺𝙱-𝙰𝟸𝙱, the largest 𝙻𝙵𝙼𝟸.𝟻 family member. It is an efficient local model for laptops and PCs to work through multi-step tasks inside popular agent harnesses. > 24B total parameters, 2B active per token > Context expanded to 131K tokens > A 128K-token vocabulary > 33T pretraining tokens > It is a reasoning model > Very easy to fine-tune and customize > Performs competitively with Qwen3.6-35B-A3B, a model with ~50% more total and active parameters, on agentic and tool-use tasks. > Open base and post-trained weights on @huggingface 🤗 1/
查看被引用的帖子
