从语言到影像，从开源到 API。读懂模型能力、比较真实成本，
为你的下一个想法，找到合适的智能引擎。
*👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord*. **Model creator:** microsoft **Original model**: Phi-4-mini-reasoning **GGUF quantization:** provided by bartowski based on `llama.cpp` release b5228 🙏 Special thanks to Georgi Gerganov and the whole team working on llama.cpp for making all of this possible.
译文排队中 · 当前显示来源原文
This model lmstudio-community/Phi-4-mini-reasoning-MLX-4bit was converted to MLX format from microsoft/Phi-4-mini-reasoning using mlx-lm version **0.24.0**.
译文排队中 · 当前显示来源原文
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
*👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord*. **Model creator:** microsoft **Original model**: Phi-4-reasoning-plus **GGUF quantization:** provided by bartowski based on `llama.cpp` release b5228 Additionally trained with Reinforcement Learning for higher accuracy but generates on average 50% more tokens
译文排队中 · 当前显示来源原文
This model lmstudio-community/Phi-4-reasoning-plus-MLX-4bit was converted to MLX format from microsoft/Phi-4-reasoning-plus using mlx-lm version **0.24.0**.
译文排队中 · 当前显示来源原文
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
*👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord*. **Model creator:** Qwen **Original model**: Qwen2.5-0.5B-Instruct **GGUF quantization:** provided by bartowski based on `llama.cpp` release b3772 Over 29 languages including Chinese, English, French, Spanish, Portuguese, German, Italian, Russian, Japanese, Korean, Vietnamese, Thai, and Arabic.
译文排队中 · 当前显示来源原文
*👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord*. Compatibility: Apple Silicon Macs **Model creator:** Qwen **Original model**: Qwen2.5-0.5B-Instruct **MLX quantizations:** provided by bartowski from mlx-examples Over 29 languages including Chinese, English, French, Spanish, Portuguese, German, Italian, Russian, Japanese, Korean, Vietnamese, Thai, and Arabic.
译文排队中 · 当前显示来源原文
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
*👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord*. **Model creator:** Qwen **Original model**: Qwen2.5-1.5B-Instruct **GGUF quantization:** provided by bartowski based on `llama.cpp` release b3772 Over 29 languages including Chinese, English, French, Spanish, Portuguese, German, Italian, Russian, Japanese, Korean, Vietnamese, Thai, and Arabic.
译文排队中 · 当前显示来源原文
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
*👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord*. **Model creator:** Qwen **Original model**: Qwen2.5-14B-Instruct-1M **GGUF quantization:** provided by bartowski based on `llama.cpp` release b4546 Significantly improved performance in handling long-context tasks while maintaining its capability in short tasks.
译文排队中 · 当前显示来源原文
*👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord*. **Model creator:** Qwen **Original model**: Qwen2.5-14B-Instruct **GGUF quantization:** provided by bartowski based on `llama.cpp` release b3772 Over 29 languages including Chinese, English, French, Spanish, Portuguese, German, Italian, Russian, Japanese, Korean, Vietnamese, Thai, and Arabic.
译文排队中 · 当前显示来源原文
*👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord*. Compatibility: Apple Silicon Macs **Model creator:** Qwen **Original model**: Qwen2.5-14B-Instruct **MLX quantizations:** provided by bartowski from mlx-examples Over 29 languages including Chinese, English, French, Spanish, Portuguese, German, Italian, Russian, Japanese, Korean, Vietnamese, Thai, and Arabic.
译文排队中 · 当前显示来源原文
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
*👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord*. **Model creator:** Qwen **Original model**: Qwen2.5-3B-Instruct **GGUF quantization:** provided by bartowski based on `llama.cpp` release b3772 Over 29 languages including Chinese, English, French, Spanish, Portuguese, German, Italian, Russian, Japanese, Korean, Vietnamese, Thai, and Arabic.
译文排队中 · 当前显示来源原文
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
可以调整厂商、分类或输入输出条件；新模型正持续收录。
调整月度 Token 用量，直观比较不同模型的预估 API 开支。
使用已采集且单位可比的 USD / 百万 Token 渠道报价。报价为采集时快照；不计缓存优惠、阶梯价、推理额外输出与税费，请以来源的当前报价为准。
先区分输入、输出和缓存价格，再使用同一任务和用量估算总费用。图像、音频和视频可能按张、时长或分辨率计费，不能直接与 Token 单价比较。
不一定。必须逐一核对具体模型版本的许可证、商用限制及使用政策。自己部署还需要考虑显存、推理资源和运维费用。
榜单取决于测试任务、版本与评测方法。建议用实际业务样本比较准确性、时延、稳定性和成本，再选择模型。
