commit 5226a00fb75e969d6fa25aa0e8d8de1a154425ca Author: ModelHub XC Date: Tue Sep 1 20:46:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.2-3B-All-Mix-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f21755d --- /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-3.2-3B-All-Mix.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-All-Mix.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-All-Mix.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-All-Mix.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-All-Mix.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-All-Mix.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-All-Mix.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-All-Mix.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-All-Mix.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-All-Mix.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-All-Mix.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-All-Mix.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.2-3B-All-Mix.IQ4_XS.gguf b/Llama-3.2-3B-All-Mix.IQ4_XS.gguf new file mode 100644 index 0000000..3596cb1 --- /dev/null +++ b/Llama-3.2-3B-All-Mix.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bed26a6bc9eb4f5491e7e185ff2a8bcb0d6f2bee675a69cc662d60d720662c37 +size 2050221472 diff --git a/Llama-3.2-3B-All-Mix.Q2_K.gguf b/Llama-3.2-3B-All-Mix.Q2_K.gguf new file mode 100644 index 0000000..5cb0c44 --- /dev/null +++ b/Llama-3.2-3B-All-Mix.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebb2690d2e48eb6b57777d5eca76ae6bcb4e3d49bd281d476bed3696323a9b65 +size 1493218720 diff --git a/Llama-3.2-3B-All-Mix.Q3_K_L.gguf b/Llama-3.2-3B-All-Mix.Q3_K_L.gguf new file mode 100644 index 0000000..6683090 --- /dev/null +++ b/Llama-3.2-3B-All-Mix.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0210e0582fb5728469bbadf0f888654aa9119d6a3b619d86c7bb75c823e39bf9 +size 1984646560 diff --git a/Llama-3.2-3B-All-Mix.Q3_K_M.gguf b/Llama-3.2-3B-All-Mix.Q3_K_M.gguf new file mode 100644 index 0000000..78b8741 --- /dev/null +++ b/Llama-3.2-3B-All-Mix.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da26ad604902a1f8cce3fd442e94eddb7fcd8bfb58478dc2df77e2d5d0a49395 +size 1856458144 diff --git a/Llama-3.2-3B-All-Mix.Q3_K_S.gguf b/Llama-3.2-3B-All-Mix.Q3_K_S.gguf new file mode 100644 index 0000000..8e056fe --- /dev/null +++ b/Llama-3.2-3B-All-Mix.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dfc6f3957487024ff6c35d96d8bf632e97c48126a6d3355cab6cd4a4b8978572 +size 1712147872 diff --git a/Llama-3.2-3B-All-Mix.Q4_K_M.gguf b/Llama-3.2-3B-All-Mix.Q4_K_M.gguf new file mode 100644 index 0000000..2c5192c --- /dev/null +++ b/Llama-3.2-3B-All-Mix.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3519f60a190ddc85a10f8dda8c028f54528d4ed1e9dba66d55d577525c3015a6 +size 2241004960 diff --git a/Llama-3.2-3B-All-Mix.Q4_K_S.gguf b/Llama-3.2-3B-All-Mix.Q4_K_S.gguf new file mode 100644 index 0000000..39a3c57 --- /dev/null +++ b/Llama-3.2-3B-All-Mix.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22db1a25318cd905c83dc0f3dd21c2c116f47af6ab8c18a4f5c2ebe38961b30f +size 2149828000 diff --git a/Llama-3.2-3B-All-Mix.Q5_K_M.gguf b/Llama-3.2-3B-All-Mix.Q5_K_M.gguf new file mode 100644 index 0000000..e4a1acf --- /dev/null +++ b/Llama-3.2-3B-All-Mix.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92494fd5f0c41d9c31b093eca4a4900d72ab0a4e4a17d5355b33a2dd7896e391 +size 2593031584 diff --git a/Llama-3.2-3B-All-Mix.Q5_K_S.gguf b/Llama-3.2-3B-All-Mix.Q5_K_S.gguf new file mode 100644 index 0000000..c3aadef --- /dev/null +++ b/Llama-3.2-3B-All-Mix.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d9150692b097ce0aae6e53b04b2ec4ac8b9c092209d43c1e2ed29b80be2a7c4 +size 2540389792 diff --git a/Llama-3.2-3B-All-Mix.Q6_K.gguf b/Llama-3.2-3B-All-Mix.Q6_K.gguf new file mode 100644 index 0000000..abe1c41 --- /dev/null +++ b/Llama-3.2-3B-All-Mix.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6ee37697285fddd478cfa9bf81d362b5c88c1fd8ffb411d8823f6267af1bdcb +size 2967059872 diff --git a/Llama-3.2-3B-All-Mix.Q8_0.gguf b/Llama-3.2-3B-All-Mix.Q8_0.gguf new file mode 100644 index 0000000..d0c07a0 --- /dev/null +++ b/Llama-3.2-3B-All-Mix.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c2a2de7b11833005a508f858d21d9c84e518dd45dfce945e230ab5a7a997dc6 +size 3840527776 diff --git a/Llama-3.2-3B-All-Mix.f16.gguf b/Llama-3.2-3B-All-Mix.f16.gguf new file mode 100644 index 0000000..ac2c28c --- /dev/null +++ b/Llama-3.2-3B-All-Mix.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:014ab6547b62cf9d41818c146fc055d8c2d8d20effdd3bf940a2cdaa2b3654b4 +size 7221693856 diff --git a/README.md b/README.md new file mode 100644 index 0000000..cecf7ed --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: bunnycore/Llama-3.2-3B-All-Mix +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/bunnycore/Llama-3.2-3B-All-Mix + + +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-All-Mix-GGUF/resolve/main/Llama-3.2-3B-All-Mix.Q2_K.gguf) | Q2_K | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-All-Mix-GGUF/resolve/main/Llama-3.2-3B-All-Mix.Q3_K_S.gguf) | Q3_K_S | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-All-Mix-GGUF/resolve/main/Llama-3.2-3B-All-Mix.Q3_K_M.gguf) | Q3_K_M | 2.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-All-Mix-GGUF/resolve/main/Llama-3.2-3B-All-Mix.Q3_K_L.gguf) | Q3_K_L | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-All-Mix-GGUF/resolve/main/Llama-3.2-3B-All-Mix.IQ4_XS.gguf) | IQ4_XS | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-All-Mix-GGUF/resolve/main/Llama-3.2-3B-All-Mix.Q4_K_S.gguf) | Q4_K_S | 2.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-All-Mix-GGUF/resolve/main/Llama-3.2-3B-All-Mix.Q4_K_M.gguf) | Q4_K_M | 2.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-All-Mix-GGUF/resolve/main/Llama-3.2-3B-All-Mix.Q5_K_S.gguf) | Q5_K_S | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-All-Mix-GGUF/resolve/main/Llama-3.2-3B-All-Mix.Q5_K_M.gguf) | Q5_K_M | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-All-Mix-GGUF/resolve/main/Llama-3.2-3B-All-Mix.Q6_K.gguf) | Q6_K | 3.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-All-Mix-GGUF/resolve/main/Llama-3.2-3B-All-Mix.Q8_0.gguf) | Q8_0 | 3.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-All-Mix-GGUF/resolve/main/Llama-3.2-3B-All-Mix.f16.gguf) | f16 | 7.3 | 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. + +