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。
All quants made using imatrix option with dataset from here Run them directly with llama.cpp, or any other llama.cpp based project This model has vision capabilities, more details here: https://github.com/ggml-org/llama.cpp/pull/12344
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。
All quants made using imatrix option with dataset from here Run them directly with llama.cpp, or any other llama.cpp based project Some of these quants (Q3_K_XL, Q4_K_L etc) are the standard quantization method with the embeddings and output weights quantized to Q8_0 instead of what they would normally default to.
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。
This model has vision capabilities, more details here: https://github.com/ggml-org/llama.cpp/pull/12344 Some of these quants (Q3_K_XL, Q4_K_L etc) are the standard quantization method with the embeddings and output weights quantized to Q8_0 instead of what they would normally default to. If the model is bigger than 50GB, it will have been split into multiple files. In order to download them all to a local folder, run:
译文排队中 · 当前显示来源原文
*ONLY* Q4_0 is expected to be better, but figured while I'm at it I might as well make others to see what happens? gemma-3-27b-it-qat-Q4_0.gguf | Q4_0 | 15.62GB | Should be improved due to QAT, offers online repacking for ARM and AVX CPU inference. Some of these quants (Q3_K_XL, Q4_K_L etc) are the standard quantization method with the embeddings and output weights quantized to Q8_0 instead of what they would normally default to.
译文排队中 · 当前显示来源原文
All quants made using imatrix option with dataset from here Run them directly with llama.cpp, or any other llama.cpp based project This model has vision capabilities, more details here: https://github.com/ggml-org/llama.cpp/pull/12344
译文排队中 · 当前显示来源原文
*ONLY* Q4_0 is expected to be better, but figured while I'm at it I might as well make others to see what happens? gemma-3-4b-it-qat-Q4_0.gguf | Q4_0 | 2.37GB | false | Should be improved due to QAT, offers online repacking for ARM and AVX CPU inference. Some of these quants (Q3_K_XL, Q4_K_L etc) are the standard quantization method with the embeddings and output weights quantized to Q8_0 instead of what they would normally default to.
译文排队中 · 当前显示来源原文
No chat template specified so default is used. This may be incorrect, check original model card for details. Some of these quants (Q3_K_XL, Q4_K_L etc) are the standard quantization method with the embeddings and output weights quantized to Q8_0 instead of what they would normally default to. If the model is bigger than 50GB, it will have been split into multiple files. In order to download them all to a local folder, run:
译文排队中 · 当前显示来源原文
No chat template specified so default is used. This may be incorrect, check original model card for details. Some of these quants (Q3_K_XL, Q4_K_L etc) are the standard quantization method with the embeddings and output weights quantized to Q8_0 instead of what they would normally default to. If the model is bigger than 50GB, it will have been split into multiple files. In order to download them all to a local folder, run:
译文排队中 · 当前显示来源原文
All quants made using imatrix option with dataset from here - llama.cpp - ramalama - LM Studio - koboldcpp - Jan AI - Text Generation Web UI - LoLLMs Note: if it's a newly supported model, you may need to wait for an update from the developers.
译文排队中 · 当前显示来源原文
All quants made using imatrix option with dataset from here - llama.cpp - ramalama - LM Studio - koboldcpp - Jan AI - Text Generation Web UI - LoLLMs Note: if it's a newly supported model, you may need to wait for an update from the developers.
译文排队中 · 当前显示来源原文
All quants made using imatrix option with dataset from here - llama.cpp - ramalama - LM Studio - koboldcpp - Jan AI - Text Generation Web UI - LoLLMs Note: if it's a newly supported model, you may need to wait for an update from the developers.
译文排队中 · 当前显示来源原文
All quants made using imatrix option with dataset from here - llama.cpp - ramalama - LM Studio - koboldcpp - Jan AI - Text Generation Web UI - LoLLMs Note: if it's a newly supported model, you may need to wait for an update from the developers.
译文排队中 · 当前显示来源原文
Some of these quants (Q3_K_XL, Q4_K_L etc) are the standard quantization method with the embeddings and output weights quantized to Q8_0 instead of what they would normally default to. If the model is bigger than 50GB, it will have been split into multiple files. In order to download them all to a local folder, run: You can either specify a new local-dir (google_medgemma-27b-it-Q8_0) or download them all in place (./)
译文排队中 · 当前显示来源原文
Some of these quants (Q3_K_XL, Q4_K_L etc) are the standard quantization method with the embeddings and output weights quantized to Q8_0 instead of what they would normally default to. If the model is bigger than 50GB, it will have been split into multiple files. In order to download them all to a local folder, run: You can either specify a new local-dir (google_medgemma-4b-it-Q8_0) or download them all in place (./)
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
If you're using an ARM chip, the Q4_0_X_X quants will have a substantial speedup. Check out Q4_0_4_4 speed comparisons on the original pull request To check which one would work best for your ARM chip, you can check AArch64 SoC features(thanks EloyOn!). Some of these quants (Q3_K_XL, Q4_K_L etc) are the standard quantization method with the embeddings and output weights quantized to Q8_0 instead of what they would normally default to.
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
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。
