From 039239d47eab2ef42d7e260ab32ae6001d0672a6 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Thu, 7 May 2026 07:20:50 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: mradermacher/Llama-3.3-Mini-Instruct-GGUF Source: Original Platform --- .gitattributes | 47 ++++++++++++++++++++ Llama-3.3-Mini-Instruct.IQ4_XS.gguf | 3 ++ Llama-3.3-Mini-Instruct.Q2_K.gguf | 3 ++ Llama-3.3-Mini-Instruct.Q3_K_L.gguf | 3 ++ Llama-3.3-Mini-Instruct.Q3_K_M.gguf | 3 ++ Llama-3.3-Mini-Instruct.Q3_K_S.gguf | 3 ++ Llama-3.3-Mini-Instruct.Q4_K_M.gguf | 3 ++ Llama-3.3-Mini-Instruct.Q4_K_S.gguf | 3 ++ Llama-3.3-Mini-Instruct.Q5_K_M.gguf | 3 ++ Llama-3.3-Mini-Instruct.Q5_K_S.gguf | 3 ++ Llama-3.3-Mini-Instruct.Q6_K.gguf | 3 ++ Llama-3.3-Mini-Instruct.Q8_0.gguf | 3 ++ Llama-3.3-Mini-Instruct.f16.gguf | 3 ++ README.md | 66 +++++++++++++++++++++++++++++ 14 files changed, 149 insertions(+) create mode 100644 .gitattributes create mode 100644 Llama-3.3-Mini-Instruct.IQ4_XS.gguf create mode 100644 Llama-3.3-Mini-Instruct.Q2_K.gguf create mode 100644 Llama-3.3-Mini-Instruct.Q3_K_L.gguf create mode 100644 Llama-3.3-Mini-Instruct.Q3_K_M.gguf create mode 100644 Llama-3.3-Mini-Instruct.Q3_K_S.gguf create mode 100644 Llama-3.3-Mini-Instruct.Q4_K_M.gguf create mode 100644 Llama-3.3-Mini-Instruct.Q4_K_S.gguf create mode 100644 Llama-3.3-Mini-Instruct.Q5_K_M.gguf create mode 100644 Llama-3.3-Mini-Instruct.Q5_K_S.gguf create mode 100644 Llama-3.3-Mini-Instruct.Q6_K.gguf create mode 100644 Llama-3.3-Mini-Instruct.Q8_0.gguf create mode 100644 Llama-3.3-Mini-Instruct.f16.gguf create mode 100644 README.md diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..b79269b --- /dev/null +++ b/.gitattributes @@ -0,0 +1,47 @@ +*.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 +Llama-3.3-Mini-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-Mini-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-Mini-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-Mini-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-Mini-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-Mini-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-Mini-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-Mini-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-Mini-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-Mini-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-Mini-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-Mini-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.3-Mini-Instruct.IQ4_XS.gguf b/Llama-3.3-Mini-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..44b0106 --- /dev/null +++ b/Llama-3.3-Mini-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e4296f1cc5af8d1117bafac560e70e6d11bc183ebbf75a8468996f520c9ae91 +size 6023952640 diff --git a/Llama-3.3-Mini-Instruct.Q2_K.gguf b/Llama-3.3-Mini-Instruct.Q2_K.gguf new file mode 100644 index 0000000..6e20df3 --- /dev/null +++ b/Llama-3.3-Mini-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1236007e1129e9b3342c2ee3494e1b2c4f53f84368cb17c857cb51d44736c97 +size 4349081856 diff --git a/Llama-3.3-Mini-Instruct.Q3_K_L.gguf b/Llama-3.3-Mini-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..1f5ad46 --- /dev/null +++ b/Llama-3.3-Mini-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4906fad5ba81ff4cbe52423824c60b52b9a8dd782cf6d17817a1c1d6ac9f09b +size 5798623488 diff --git a/Llama-3.3-Mini-Instruct.Q3_K_M.gguf b/Llama-3.3-Mini-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..e6c1ddc --- /dev/null +++ b/Llama-3.3-Mini-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:071b62afdb442e95a36c04b12b411c9a552fd364449295b0663bcb6844255860 +size 5412747520 diff --git a/Llama-3.3-Mini-Instruct.Q3_K_S.gguf b/Llama-3.3-Mini-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..9823941 --- /dev/null +++ b/Llama-3.3-Mini-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d766204f9c1e94739ca03031722662232866ed7b3bceed1fdebe2ea0ab931d7 +size 4998428928 diff --git a/Llama-3.3-Mini-Instruct.Q4_K_M.gguf b/Llama-3.3-Mini-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..c42136f --- /dev/null +++ b/Llama-3.3-Mini-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:461858d28db2644e20cb2f119adf4160e20057fed8815c853ef5a61868d8b127 +size 6587955456 diff --git a/Llama-3.3-Mini-Instruct.Q4_K_S.gguf b/Llama-3.3-Mini-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..00321ca --- /dev/null +++ b/Llama-3.3-Mini-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3093691d19de68b9ff29a6f41d1dd4a95b70fc395912de3c28d1436df7d572de +size 6307920128 diff --git a/Llama-3.3-Mini-Instruct.Q5_K_M.gguf b/Llama-3.3-Mini-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..08b4972 --- /dev/null +++ b/Llama-3.3-Mini-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ea2648a0955921fef45224c8147c07ada99fa65921026b40ea470dfe9fcfc46 +size 7636793600 diff --git a/Llama-3.3-Mini-Instruct.Q5_K_S.gguf b/Llama-3.3-Mini-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..d810c68 --- /dev/null +++ b/Llama-3.3-Mini-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb9cd7169767162f2024c9e0244e6f197ef2352848c2bfa829ed174f1f4b8dcc +size 7475247360 diff --git a/Llama-3.3-Mini-Instruct.Q6_K.gguf b/Llama-3.3-Mini-Instruct.Q6_K.gguf new file mode 100644 index 0000000..05d3001 --- /dev/null +++ b/Llama-3.3-Mini-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:583ad3d5820a2fd1a5fb76bf5f3d2bde3c34bd1b79e35e48e8f2da4a2c1e48d7 +size 8751184128 diff --git a/Llama-3.3-Mini-Instruct.Q8_0.gguf b/Llama-3.3-Mini-Instruct.Q8_0.gguf new file mode 100644 index 0000000..b31a5ae --- /dev/null +++ b/Llama-3.3-Mini-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:efe03dc09b336a9cf581d28af29a91cf61a698c0f0d19da845d883616be1b535 +size 11332352256 diff --git a/Llama-3.3-Mini-Instruct.f16.gguf b/Llama-3.3-Mini-Instruct.f16.gguf new file mode 100644 index 0000000..f2296b6 --- /dev/null +++ b/Llama-3.3-Mini-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ff1e40e37dbcb21bd125f58a9af1d18c5c96940a1f6e479ae904637cc98dd54 +size 21323970816 diff --git a/README.md b/README.md new file mode 100644 index 0000000..9023e8e --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: mergekit-community/Llama-3.3-Mini-Instruct +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/mergekit-community/Llama-3.3-Mini-Instruct + + +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/Llama-3.3-Mini-Instruct-GGUF/resolve/main/Llama-3.3-Mini-Instruct.Q2_K.gguf) | Q2_K | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-Mini-Instruct-GGUF/resolve/main/Llama-3.3-Mini-Instruct.Q3_K_S.gguf) | Q3_K_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-Mini-Instruct-GGUF/resolve/main/Llama-3.3-Mini-Instruct.Q3_K_M.gguf) | Q3_K_M | 5.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-Mini-Instruct-GGUF/resolve/main/Llama-3.3-Mini-Instruct.Q3_K_L.gguf) | Q3_K_L | 5.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-Mini-Instruct-GGUF/resolve/main/Llama-3.3-Mini-Instruct.IQ4_XS.gguf) | IQ4_XS | 6.1 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-Mini-Instruct-GGUF/resolve/main/Llama-3.3-Mini-Instruct.Q4_K_S.gguf) | Q4_K_S | 6.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-Mini-Instruct-GGUF/resolve/main/Llama-3.3-Mini-Instruct.Q4_K_M.gguf) | Q4_K_M | 6.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-Mini-Instruct-GGUF/resolve/main/Llama-3.3-Mini-Instruct.Q5_K_S.gguf) | Q5_K_S | 7.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-Mini-Instruct-GGUF/resolve/main/Llama-3.3-Mini-Instruct.Q5_K_M.gguf) | Q5_K_M | 7.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-Mini-Instruct-GGUF/resolve/main/Llama-3.3-Mini-Instruct.Q6_K.gguf) | Q6_K | 8.9 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-Mini-Instruct-GGUF/resolve/main/Llama-3.3-Mini-Instruct.Q8_0.gguf) | Q8_0 | 11.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-Mini-Instruct-GGUF/resolve/main/Llama-3.3-Mini-Instruct.f16.gguf) | f16 | 21.4 | 16 bpw, overkill | + +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. + +