gemma-2-2b-it-llamafile
mozilla-ai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。
输入 待核验→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗DISCOVER & COMPARE
探索 AI 模型 26
gemma-2-9b-it-llamafile
mozilla-ai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
输入 待核验→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗Llama-3.2-1B-Instruct-llamafile
mozilla-aiThis is a large language model that was released by Meta on 2024-09-25. This edition of LLaMA packs a lot of quality in a size small enough to run on most computers with 4GB+ of RAM. See also its sister model Llama-3.2-1B-Instruct-llamafile. Mozilla packaged the LLaMA 3.2 models into executable weights that we call llamafiles. This gives you the easiest fastest way to use the model on Linux, MacOS, Windows, FreeBSD, OpenBSD and NetBSD systems you control on both AMD64 and ARM64. To get started, you need both the LLaMA 3.2 weights, and the llamafile software. Both of them are included in a single file, which can be downloaded and run as follows:
译文排队中 · 当前显示来源原文
输入 待核验→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗Llama-3.2-3B-Instruct-llamafile
mozilla-ai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。
输入 待核验→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗llamafile_0.10
mozilla-aiThese llamafiles are pre-packaged with support for CPU, Metal GPUs on Mac and CUDA+Vulkan on linux and Windows. If you have a different GPU or OS, you can download the corresponding library in the Files and versions section and save it in your home directory for llamafile to automatically find it. For more information about our project, check out our github repo. To learn how to use llamafiles, check our documentation! *NOTE*: While the llamafile project is Apache 2.0-licensed, the licenses of models we bundle with it might differ. Use the table above for reference.
译文排队中 · 当前显示来源原文
输入 待核验→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗llava-v1.5-7b-llamafile
mozilla-ai**Model type:** LLaVA is an open-source chatbot trained by fine-tuning LLaMA/Vicuna on GPT-generated multimodal instruction-following data. It is an auto-regressive language model, based on the transformer architecture. Llama 2 is licensed under the LLAMA 2 Community License, Copyright (c) Meta Platforms, Inc. All Rights Reserved. **Where to send questions or comments about the model:** https://github.com/haotian-liu/LLaVA/issues
译文排队中 · 当前显示来源原文
输入 待核验→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗llm-compiler-13b-ftd-llamafile
mozilla-ai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
输入 待核验→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗mathstral-7B-v0.1-llamafile
mozilla-ai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。
输入 待核验→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗Meta-Llama-3.1-405B-Instruct-llamafile
mozilla-ai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
输入 待核验→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗Meta-Llama-3.1-405B-llamafile
mozilla-ai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
输入 待核验→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗Meta-Llama-3.1-70B-Instruct-llamafile
mozilla-ai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
输入 待核验→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗Meta-Llama-3.1-8B-Instruct-llamafile
mozilla-aiThis is a large language model that was released by Meta on 2024-07-23. It was fine-tuned by Meta to follow your instructions. It's big enough to be capable of being put to serious use, and it's small enough to be capable of running on most personal computers. Mozilla has packaged the LLaMA model into executable weights that we call llamafiles. This gives you the easiest fastest way to use the model on Linux, MacOS, Windows, FreeBSD, OpenBSD 7.3, and NetBSD systems you control on both AMD64 and ARM64. To get started, you need both the LLaMA weights, and the llamafile software. Both of them are included in a single file, which can be downloaded and run as follows:
译文排队中 · 当前显示来源原文
输入 待核验→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗Meta-Llama-3.1-8B-llamafile
mozilla-aiThis is a large language model that was released by Meta on 2024-07-23. It's big enough to be capable of being put to serious use, and it's small enough to be capable of running on most personal computers. This repo contains the base model, which has not been fine-tuned to follow instructions. Mozilla has packaged the LLaMA model into executable weights that we call llamafiles. This gives you the easiest fastest way to use the model on Linux, MacOS, Windows, FreeBSD, OpenBSD and NetBSD systems you control on both AMD64 and ARM64. You can then use the completion mode of the GUI to experiment with this model. You can prompt the model for completions on the command line too:
译文排队中 · 当前显示来源原文
输入 待核验→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗Meta-Llama-3-8B-Instruct-llamafile
mozilla-aiThis repository contains executable weights (which we call llamafiles) that run on Linux, MacOS, Windows, FreeBSD, OpenBSD, and NetBSD for AMD64 and ARM64. Running the following on a desktop OS will launch a tab in your web browser with a chatbot interface. llamafile is a new format introduced by Mozilla Ocho on Nov 20th 2023. It uses Cosmopolitan Libc to turn LLM weights into runnable llama.cpp binaries that run on the stock installs of six OSes for both ARM64 and AMD64.
译文排队中 · 当前显示来源原文
输入 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗Mistral-7B-Instruct-v0.2-llamafile
mozilla-aiWARNING: This README may contain inaccuracies. It was generated automatically by forking TheBloke/Mistral-7B-Instruct-v0.2-GGUF and piping the README through sed. Errors should be reported to jartine, and do not reflect TheBloke. You can also support his work on Patreon. llamafile is a new format introduced by Mozilla Ocho on Nov 20th 2023. It uses Cosmopolitan Libc to turn LLM weights into runnable llama.cpp binaries that run on the stock installs of six OSes for both ARM64 and AMD64. These quantised llamafilev2 files are compatible with llama.cpp from August 27th onwards, as of commit d0cee0d
译文排队中 · 当前显示来源原文
输入 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗Mistral-7B-Instruct-v0.3-llamafile
mozilla-aiThis repository contains executable weights (which we call llamafiles) that run on Linux, MacOS, Windows, FreeBSD, OpenBSD, and NetBSD for AMD64 and ARM64. The third edition of Mistral 7B was released on May 22th, 2024. It increases the vocabulary size to 32768, supports the v3 tokenizer, and introduces support for function calling. Assuming your system has at least 16GB of RAM, you can try running the following command which download, concatenate, and execute the model.
译文排队中 · 当前显示来源原文
输入 待核验→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗Mistral-Nemo-Instruct-2407-llamafile
mozilla-ai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
输入 待核验→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗Mixtral-8x7B-Instruct-v0.1-llamafile
mozilla-ai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
输入 待核验→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗OLMo-7B-0424-llamafile
mozilla-ai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
输入 待核验→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗Phi-3-medium-128k-instruct-llamafile
mozilla-aiThis is a large language model that was released by Microsoft on May 21st, 2024. It has an outstanding context size, which makes it good for summarizing and extracting information from large bodies of text. It's also been fine-tuned to follow your instructions. Mozilla has packaged the Phi-3 model into executable weights that we call llamafiles. This gives you the easiest fastest way to use the model on Linux, MacOS, Windows, FreeBSD, OpenBSD and NetBSD systems you control on both AMD64 and ARM64. Running the following on a desktop OS will launch a tab in your web browser with both a chatbot interface and a completion interface.
译文排队中 · 当前显示来源原文
输入 待核验→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗Phi-3-mini-4k-instruct-llamafile
mozilla-aiThis repository contains executable weights (which we call llamafiles) that run on Linux, MacOS, Windows, FreeBSD, OpenBSD, and NetBSD for AMD64 and ARM64. Assuming your system has at least 32GB of RAM, you can try running the following command which download, concatenate, and execute the model. Alternatively, you may download an official `llamafile` executable from Mozilla Ocho on GitHub, in which case you can use the Mixtral llamafiles as a simple weights data file.
译文排队中 · 当前显示来源原文
输入 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗rocket-3B-llamafile
mozilla-ai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。
输入 待核验→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗tiny-pii-electra-small
mozilla-ai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
输入 待核验→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗TinyLlama-1.1B-Chat-v1.0-llamafile
mozilla-ai- Model creator: TinyLlama - Original model: TinyLlama-1.1B-Chat-v1.0 - Prebuilt llamafiles for each quantization format that can be executed to launch a web server or cli interface - GGUF weights data files for each quantization format, which require either the llamafile or llama.cpp software to run
译文排队中 · 当前显示来源原文
输入 待核验→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗暂未找到匹配模型
可以调整厂商、分类或输入输出条件；新模型正持续收录。
COST EXPLORER
好模型，也要算好成本。
调整月度 Token 用量，直观比较不同模型的预估 API 开支。
1 M = 100 万 Token · 美元计价
仅比较同一渠道的基础文本 Token 报价
仅比较同一渠道的基础文本 Token 报价
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。
MODEL HANDBOOK
读懂模型，再做选择
API 价格应该怎么比较？+
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。
开放权重，就代表可以免费商用吗？+
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。
排行榜第一，就是最适合我的模型吗？+
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。