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 (OLMo-2-1124-13B-Instruct-Q8_0) or download them all in place (./)
译文排队中 · 当前显示来源原文
输入 文本→ 输出 文本
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 文本→ 输出 文本
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. Some say that this improves the quality, others don't notice any difference. If you use these models PLEASE COMMENT with your findings. I would like feedback that these are actually used and useful so I don't keep uploading quants no one is using. 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
输入 文本→ 输出 文本
**Model details:** - Parameter count: 1B (source checkpoint) - Input support: text, image (with mmproj file) - details - Speculative decoding: no - imatrix: yes - details **Don't know which to choose?** Grab Q4_K_M (0.68GB) - usually a good mix of size and performance. Download instructions available here These quants were made with llama.cpp release b11259 - if this model's architecture is newly supported, you'll need that release or newer to run them.
译文排队中 · 当前显示来源原文
输入 文本 · 图像→ 输出 文本
**Model details:** - Parameter count: 27B (source checkpoint) - Input support: text, image (with mmproj file) - details - Speculative decoding: no - imatrix: yes - details **Don't know which to choose?** Grab Q4_K_M (17.20GB) - usually a good mix of size and performance. Download instructions available here The files marked `true` in the Split column above are stored as multiple parts in a folder. To download all the parts to a local folder, run:
译文排队中 · 当前显示来源原文
输入 文本 · 图像→ 输出 文本
**Model details:** - Parameter count: 5B (source checkpoint) - Input support: text, image (with mmproj file) - details - Speculative decoding: no - imatrix: yes - details **Don't know which to choose?** Grab Q4_K_M (3.17GB) - usually a good mix of size and performance. Download instructions available here These quants were made with llama.cpp release b11259 - if this model's architecture is newly supported, you'll need that release or newer to run them.
译文排队中 · 当前显示来源原文
输入 文本 · 图像→ 输出 文本
**Model details:** - Parameter count: 9B (source checkpoint) - Input support: text, image (with mmproj file) - details - Speculative decoding: no - imatrix: yes - details **Don't know which to choose?** Grab Q4_K_M (5.84GB) - usually a good mix of size and performance. Download instructions available here These quants were made with llama.cpp release b11259 - if this model's architecture is newly supported, you'll need that release or newer to run them.
译文排队中 · 当前显示来源原文
输入 文本 · 图像→ 输出 文本
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 文本→ 输出 文本
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 文本→ 输出 文本
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 文本→ 输出 文本
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 文本→ 输出 文本
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 文本→ 输出 文本
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 文本→ 输出 文本
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 文本→ 输出 文本
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 文本→ 输出 文本
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 文本→ 输出 文本
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 文本→ 输出 文本
The reason is, the FFN (feed forward networks) of gpt-oss do not behave nicely when quantized to anything other than MXFP4, so they are kept at that level for everything. The rest of these are provided for your own interest in case you feel like experimenting, but the size savings is basically non-existent so I would not recommend running them, they are provided simply for show: 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
输入 文本→ 输出 文本
All quants keep the feed forward networks at mxfp4 for optimal performance, which does mean the size differences are negligible unfortunately, but being provided just because. No chat template specified so default is used. This may be incorrect, check original model card for details. The reason is, the FFN (feed forward networks) of gpt-oss do not behave nicely when quantized to anything other than MXFP4, so they are kept at that level for everything.
译文排队中 · 当前显示来源原文
输入 文本→ 输出 文本
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 文本→ 输出 文本
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 文本→ 输出 文本
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 文本→ 输出 文本
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 文本→ 输出 文本
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 文本→ 输出 文本
