commit ffa1b7693ab8e02848e676a67dd82c4a96cb4e96 Author: ModelHub XC Date: Thu May 14 21:10:50 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Mixtral_Mini_AI-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2beed13 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,49 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +Mixtral_Mini_AI.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Mixtral_Mini_AI.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Mixtral_Mini_AI.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mixtral_Mini_AI.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Mixtral_Mini_AI.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Mixtral_Mini_AI.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Mixtral_Mini_AI.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mixtral_Mini_AI.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mixtral_Mini_AI.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Mixtral_Mini_AI.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mixtral_Mini_AI.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mixtral_Mini_AI.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mixtral_Mini_AI.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Mixtral_Mini_AI.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Mixtral_Mini_AI.IQ3_M.gguf b/Mixtral_Mini_AI.IQ3_M.gguf new file mode 100644 index 0000000..9409558 --- /dev/null +++ b/Mixtral_Mini_AI.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f6bad9d030c1b586a59e4ac6f50939b858b668df1f5fc1ecb047974ffc29aff +size 1724733280 diff --git a/Mixtral_Mini_AI.IQ3_S.gguf b/Mixtral_Mini_AI.IQ3_S.gguf new file mode 100644 index 0000000..0c2a7f8 --- /dev/null +++ b/Mixtral_Mini_AI.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:901422b9f092cc325a9a8f1b7eb67f0e6e49cc244564ee5b9bbd07fa34763b20 +size 1673484128 diff --git a/Mixtral_Mini_AI.IQ3_XS.gguf b/Mixtral_Mini_AI.IQ3_XS.gguf new file mode 100644 index 0000000..591f7a4 --- /dev/null +++ b/Mixtral_Mini_AI.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c471515116707ac0126bb5b5e4f2adda89fcb9314ebbc48f78c0303ecb2ce12b +size 1591695200 diff --git a/Mixtral_Mini_AI.IQ4_XS.gguf b/Mixtral_Mini_AI.IQ4_XS.gguf new file mode 100644 index 0000000..2f7be9c --- /dev/null +++ b/Mixtral_Mini_AI.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:048cbb80f2922dd0aad4ca1ee735597f89e8b3f78966831013c15bcc337d8bd7 +size 2061137760 diff --git a/Mixtral_Mini_AI.Q2_K.gguf b/Mixtral_Mini_AI.Q2_K.gguf new file mode 100644 index 0000000..46ea635 --- /dev/null +++ b/Mixtral_Mini_AI.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90c5504fd4a285b77f14cebcff265ca614882b68ca9cceb6e12ed5f4f1e83c47 +size 1435252576 diff --git a/Mixtral_Mini_AI.Q3_K_L.gguf b/Mixtral_Mini_AI.Q3_K_L.gguf new file mode 100644 index 0000000..ded36aa --- /dev/null +++ b/Mixtral_Mini_AI.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56fc24c39bf3c234c4c91717c75a5978305930d8c2ec5d6e5a4c8f3ca7d45481 +size 1993299808 diff --git a/Mixtral_Mini_AI.Q3_K_M.gguf b/Mixtral_Mini_AI.Q3_K_M.gguf new file mode 100644 index 0000000..e2036b7 --- /dev/null +++ b/Mixtral_Mini_AI.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2878ba9e8e637ad50a24c93ec6dc7326c5e0fcc2a6ed72166614c20070035e00 +size 1842304864 diff --git a/Mixtral_Mini_AI.Q3_K_S.gguf b/Mixtral_Mini_AI.Q3_K_S.gguf new file mode 100644 index 0000000..04c4423 --- /dev/null +++ b/Mixtral_Mini_AI.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a89044f3daaaf0d0ca526514f262a49e32138306ebd13f1d68d000264c7bd849 +size 1664571232 diff --git a/Mixtral_Mini_AI.Q4_K_M.gguf b/Mixtral_Mini_AI.Q4_K_M.gguf new file mode 100644 index 0000000..a568ca2 --- /dev/null +++ b/Mixtral_Mini_AI.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22a4ffe3a2bbf52a8e04ca80c3e20493008bb560b79c50b4c1c0d1c57b5116bd +size 2275211104 diff --git a/Mixtral_Mini_AI.Q4_K_S.gguf b/Mixtral_Mini_AI.Q4_K_S.gguf new file mode 100644 index 0000000..4938452 --- /dev/null +++ b/Mixtral_Mini_AI.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53c21014020c72b85cc80d8629c5b73cebb233c021f7ae7a3d8c63d5a34deaa8 +size 2162227040 diff --git a/Mixtral_Mini_AI.Q5_K_M.gguf b/Mixtral_Mini_AI.Q5_K_M.gguf new file mode 100644 index 0000000..73e0b72 --- /dev/null +++ b/Mixtral_Mini_AI.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9018b767c3634efb349dff0f79312ca27587508f1551ef9d0c348799223d18b0 +size 2664888160 diff --git a/Mixtral_Mini_AI.Q5_K_S.gguf b/Mixtral_Mini_AI.Q5_K_S.gguf new file mode 100644 index 0000000..30dfe37 --- /dev/null +++ b/Mixtral_Mini_AI.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6eb0ca64c46f2789659e9fd74fd154bb23fac42be840028cc2302ecafa531eb +size 2598041440 diff --git a/Mixtral_Mini_AI.Q6_K.gguf b/Mixtral_Mini_AI.Q6_K.gguf new file mode 100644 index 0000000..36f9d56 --- /dev/null +++ b/Mixtral_Mini_AI.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d9be860311b6b91beeeba276461e90a260fa52f1c95785040c6e3debcdf53b3 +size 3078920032 diff --git a/Mixtral_Mini_AI.Q8_0.gguf b/Mixtral_Mini_AI.Q8_0.gguf new file mode 100644 index 0000000..e2b6557 --- /dev/null +++ b/Mixtral_Mini_AI.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:469d09b7e0c61e8ce841785b3149f918973908f664f816e4d7d0e769d666e01b +size 3987560288 diff --git a/README.md b/README.md new file mode 100644 index 0000000..6cc5dbe --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: LeroyDyer/Mixtral_Mini_AI +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- mistral +- trl +- sft +--- +## About + + + + + +static quants of https://huggingface.co/LeroyDyer/Mixtral_Mini_AI + + +weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. +## Usage + +If you are unsure how to use GGUF files, refer to one of [TheBloke's +READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for +more details, including on how to concatenate multi-part files. + +## Provided Quants + +(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) + +| Link | Type | Size/GB | Notes | +|:-----|:-----|--------:|:------| +| [GGUF](https://huggingface.co/mradermacher/Mixtral_Mini_AI-GGUF/resolve/main/Mixtral_Mini_AI.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Mixtral_Mini_AI-GGUF/resolve/main/Mixtral_Mini_AI.IQ3_XS.gguf) | IQ3_XS | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/Mixtral_Mini_AI-GGUF/resolve/main/Mixtral_Mini_AI.Q3_K_S.gguf) | Q3_K_S | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Mixtral_Mini_AI-GGUF/resolve/main/Mixtral_Mini_AI.IQ3_S.gguf) | IQ3_S | 1.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Mixtral_Mini_AI-GGUF/resolve/main/Mixtral_Mini_AI.IQ3_M.gguf) | IQ3_M | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Mixtral_Mini_AI-GGUF/resolve/main/Mixtral_Mini_AI.Q3_K_M.gguf) | Q3_K_M | 1.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Mixtral_Mini_AI-GGUF/resolve/main/Mixtral_Mini_AI.Q3_K_L.gguf) | Q3_K_L | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/Mixtral_Mini_AI-GGUF/resolve/main/Mixtral_Mini_AI.IQ4_XS.gguf) | IQ4_XS | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/Mixtral_Mini_AI-GGUF/resolve/main/Mixtral_Mini_AI.Q4_K_S.gguf) | Q4_K_S | 2.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Mixtral_Mini_AI-GGUF/resolve/main/Mixtral_Mini_AI.Q4_K_M.gguf) | Q4_K_M | 2.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Mixtral_Mini_AI-GGUF/resolve/main/Mixtral_Mini_AI.Q5_K_S.gguf) | Q5_K_S | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Mixtral_Mini_AI-GGUF/resolve/main/Mixtral_Mini_AI.Q5_K_M.gguf) | Q5_K_M | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/Mixtral_Mini_AI-GGUF/resolve/main/Mixtral_Mini_AI.Q6_K.gguf) | Q6_K | 3.2 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Mixtral_Mini_AI-GGUF/resolve/main/Mixtral_Mini_AI.Q8_0.gguf) | Q8_0 | 4.1 | fast, best quality | + +Here is a handy graph by ikawrakow comparing some lower-quality quant +types (lower is better): + +![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) + +And here are Artefact2's thoughts on the matter: +https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 + +## FAQ / Model Request + +See https://huggingface.co/mradermacher/model_requests for some answers to +questions you might have and/or if you want some other model quantized. + +## Thanks + +I thank my company, [nethype GmbH](https://www.nethype.de/), for letting +me use its servers and providing upgrades to my workstation to enable +this work in my free time. + +