commit 7e587282b0fff527498a5bf187541933830f84a8 Author: ModelHub XC Date: Tue Sep 8 20:55:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.2-3B-MIS_v1.0-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..0b8fbda --- /dev/null +++ b/.gitattributes @@ -0,0 +1,46 @@ +*.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-3.2-3B-MIS_v1.0.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-MIS_v1.0.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-MIS_v1.0.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-MIS_v1.0.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-MIS_v1.0.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-MIS_v1.0.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-MIS_v1.0.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-MIS_v1.0.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-MIS_v1.0.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-MIS_v1.0.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-MIS_v1.0.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.2-3B-MIS_v1.0.IQ4_XS.gguf b/Llama-3.2-3B-MIS_v1.0.IQ4_XS.gguf new file mode 100644 index 0000000..91c94c7 --- /dev/null +++ b/Llama-3.2-3B-MIS_v1.0.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0fa59a40f223f954c6a0105d4be56f044e30211943e593225e86cfd0a475eb23 +size 1840903712 diff --git a/Llama-3.2-3B-MIS_v1.0.Q2_K.gguf b/Llama-3.2-3B-MIS_v1.0.Q2_K.gguf new file mode 100644 index 0000000..e15da0a --- /dev/null +++ b/Llama-3.2-3B-MIS_v1.0.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90aafd6c4b466b9851be68d87782672906da51841983326f0937ae9a324ffd2e +size 1363932704 diff --git a/Llama-3.2-3B-MIS_v1.0.Q3_K_L.gguf b/Llama-3.2-3B-MIS_v1.0.Q3_K_L.gguf new file mode 100644 index 0000000..8ab12f6 --- /dev/null +++ b/Llama-3.2-3B-MIS_v1.0.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f5ae3714e172150af390171422be02a9ef0e5c1f57dfaed5ca21ffcfe44c476 +size 1815344672 diff --git a/Llama-3.2-3B-MIS_v1.0.Q3_K_M.gguf b/Llama-3.2-3B-MIS_v1.0.Q3_K_M.gguf new file mode 100644 index 0000000..9e38c25 --- /dev/null +++ b/Llama-3.2-3B-MIS_v1.0.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dfa6899d73eecc2cba5f070e672419dfe700bd4e3025ebbcf968f0106c685e57 +size 1687156256 diff --git a/Llama-3.2-3B-MIS_v1.0.Q3_K_S.gguf b/Llama-3.2-3B-MIS_v1.0.Q3_K_S.gguf new file mode 100644 index 0000000..11e5d51 --- /dev/null +++ b/Llama-3.2-3B-MIS_v1.0.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc879db1306290ae4cc3ce8058db4c61d1c4f177d4723c10b71a97a7ec7c6238 +size 1542845984 diff --git a/Llama-3.2-3B-MIS_v1.0.Q4_K_M.gguf b/Llama-3.2-3B-MIS_v1.0.Q4_K_M.gguf new file mode 100644 index 0000000..c7ab05a --- /dev/null +++ b/Llama-3.2-3B-MIS_v1.0.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76517fe8460da31fc525c4dd1e1f03b42804b1f03304d0aafb82687a7179f187 +size 2019374624 diff --git a/Llama-3.2-3B-MIS_v1.0.Q4_K_S.gguf b/Llama-3.2-3B-MIS_v1.0.Q4_K_S.gguf new file mode 100644 index 0000000..ea34474 --- /dev/null +++ b/Llama-3.2-3B-MIS_v1.0.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39e4d9f0676624dfb5809c2297b19427e8c7c6fe8dd4ff010cc522349dd82e7e +size 1928197664 diff --git a/Llama-3.2-3B-MIS_v1.0.Q5_K_M.gguf b/Llama-3.2-3B-MIS_v1.0.Q5_K_M.gguf new file mode 100644 index 0000000..16f48f5 --- /dev/null +++ b/Llama-3.2-3B-MIS_v1.0.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e07cb87fbfe654dc4dd1b13e4e6bd28c2f0a69f7230fab9ff0a0408e0a43787 +size 2322150944 diff --git a/Llama-3.2-3B-MIS_v1.0.Q5_K_S.gguf b/Llama-3.2-3B-MIS_v1.0.Q5_K_S.gguf new file mode 100644 index 0000000..43ee7db --- /dev/null +++ b/Llama-3.2-3B-MIS_v1.0.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de5d6b366499eb0c0db0159d9b283af788b9ccb7f74571cda90394e61a1df2fe +size 2269509152 diff --git a/Llama-3.2-3B-MIS_v1.0.Q6_K.gguf b/Llama-3.2-3B-MIS_v1.0.Q6_K.gguf new file mode 100644 index 0000000..0d77e1f --- /dev/null +++ b/Llama-3.2-3B-MIS_v1.0.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4c3e67e2162b1c5ae7ef8e6b9bdd010910cbd0cd5f7087636feb776ed9ff413 +size 2643850784 diff --git a/Llama-3.2-3B-MIS_v1.0.Q8_0.gguf b/Llama-3.2-3B-MIS_v1.0.Q8_0.gguf new file mode 100644 index 0000000..3bb6deb --- /dev/null +++ b/Llama-3.2-3B-MIS_v1.0.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ce449253c11c1e93cb3e9c82b4b501153b42f002b5f2582e377b42c1f36b2be +size 3421896224 diff --git a/Llama-3.2-3B-MIS_v1.0.f16.gguf b/Llama-3.2-3B-MIS_v1.0.f16.gguf new file mode 100644 index 0000000..37f9cca --- /dev/null +++ b/Llama-3.2-3B-MIS_v1.0.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be7c46cbcccee22df697b3a8af49b502a90f69e08bb06f5e394b7c794a1418d2 +size 6433685024 diff --git a/README.md b/README.md new file mode 100644 index 0000000..65466e8 --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: suzii/Llama-3.2-3B-MIS_v1.0 +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/suzii/Llama-3.2-3B-MIS_v1.0 + + +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-3.2-3B-MIS_v1.0-GGUF/resolve/main/Llama-3.2-3B-MIS_v1.0.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-MIS_v1.0-GGUF/resolve/main/Llama-3.2-3B-MIS_v1.0.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-MIS_v1.0-GGUF/resolve/main/Llama-3.2-3B-MIS_v1.0.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-MIS_v1.0-GGUF/resolve/main/Llama-3.2-3B-MIS_v1.0.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-MIS_v1.0-GGUF/resolve/main/Llama-3.2-3B-MIS_v1.0.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-MIS_v1.0-GGUF/resolve/main/Llama-3.2-3B-MIS_v1.0.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-MIS_v1.0-GGUF/resolve/main/Llama-3.2-3B-MIS_v1.0.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-MIS_v1.0-GGUF/resolve/main/Llama-3.2-3B-MIS_v1.0.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-MIS_v1.0-GGUF/resolve/main/Llama-3.2-3B-MIS_v1.0.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-MIS_v1.0-GGUF/resolve/main/Llama-3.2-3B-MIS_v1.0.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-MIS_v1.0-GGUF/resolve/main/Llama-3.2-3B-MIS_v1.0.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-MIS_v1.0-GGUF/resolve/main/Llama-3.2-3B-MIS_v1.0.f16.gguf) | f16 | 6.5 | 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. + +