commit d1f34637f75950b4befeb0c195114ac3a4a95886 Author: ModelHub XC Date: Tue Jul 21 03:30:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.2-3B-Blend-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..745dd84 --- /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-Blend.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Blend.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Blend.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Blend.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Blend.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Blend.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Blend.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Blend.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Blend.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Blend.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Blend.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Blend.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.2-3B-Blend.IQ4_XS.gguf b/Llama-3.2-3B-Blend.IQ4_XS.gguf new file mode 100644 index 0000000..a9b7400 --- /dev/null +++ b/Llama-3.2-3B-Blend.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80060df06a51e26409483c76adbbb2fef9d01a986f8c4f58271790553ca85045 +size 1840908416 diff --git a/Llama-3.2-3B-Blend.Q2_K.gguf b/Llama-3.2-3B-Blend.Q2_K.gguf new file mode 100644 index 0000000..68b88c0 --- /dev/null +++ b/Llama-3.2-3B-Blend.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8f553855a7471f969ea057c6b51b785d5b11513fe5e98c8ec84251b865f50cc +size 1363937408 diff --git a/Llama-3.2-3B-Blend.Q3_K_L.gguf b/Llama-3.2-3B-Blend.Q3_K_L.gguf new file mode 100644 index 0000000..ac97b69 --- /dev/null +++ b/Llama-3.2-3B-Blend.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65dbbe31349ed88430f86ff418c3b4b77c73a89b6266da57827aa378d28e1a81 +size 1815349376 diff --git a/Llama-3.2-3B-Blend.Q3_K_M.gguf b/Llama-3.2-3B-Blend.Q3_K_M.gguf new file mode 100644 index 0000000..2788e92 --- /dev/null +++ b/Llama-3.2-3B-Blend.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4aa0fc5fac05de374affae374f4e04e01dd2956d20cc30b59245633271b1a430 +size 1687160960 diff --git a/Llama-3.2-3B-Blend.Q3_K_S.gguf b/Llama-3.2-3B-Blend.Q3_K_S.gguf new file mode 100644 index 0000000..5d9bbbd --- /dev/null +++ b/Llama-3.2-3B-Blend.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4acc7b5eb18bacf8c0aa21eb6c8fb09b70bd3dc8889dfb50f0464ee2b6ccfecf +size 1542850688 diff --git a/Llama-3.2-3B-Blend.Q4_K_M.gguf b/Llama-3.2-3B-Blend.Q4_K_M.gguf new file mode 100644 index 0000000..3143626 --- /dev/null +++ b/Llama-3.2-3B-Blend.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4dafb412c6ac15567a09d7a7fb9dbb8b156e1cdda903cfd2e17859230f7f2e9b +size 2019379328 diff --git a/Llama-3.2-3B-Blend.Q4_K_S.gguf b/Llama-3.2-3B-Blend.Q4_K_S.gguf new file mode 100644 index 0000000..2300c9c --- /dev/null +++ b/Llama-3.2-3B-Blend.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0377b469133d2c250c37beeab93324cfa034dafcaba73da8a754e7cf43b24cd +size 1928202368 diff --git a/Llama-3.2-3B-Blend.Q5_K_M.gguf b/Llama-3.2-3B-Blend.Q5_K_M.gguf new file mode 100644 index 0000000..7a269eb --- /dev/null +++ b/Llama-3.2-3B-Blend.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae6771eb8a8bc8a543a3bf28f00c1cf92a69fbfc2c577590744e01cc7bdec16c +size 2322155648 diff --git a/Llama-3.2-3B-Blend.Q5_K_S.gguf b/Llama-3.2-3B-Blend.Q5_K_S.gguf new file mode 100644 index 0000000..fa9da31 --- /dev/null +++ b/Llama-3.2-3B-Blend.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:607305aa0cdc8673538ab0dc70bb0ce5ca3e632328d53b535dda4774cf070edc +size 2269513856 diff --git a/Llama-3.2-3B-Blend.Q6_K.gguf b/Llama-3.2-3B-Blend.Q6_K.gguf new file mode 100644 index 0000000..cfc6902 --- /dev/null +++ b/Llama-3.2-3B-Blend.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4075e93a258b71321a018b126288e59abab5d1fed29438bc55a7acebc699b62d +size 2643855488 diff --git a/Llama-3.2-3B-Blend.Q8_0.gguf b/Llama-3.2-3B-Blend.Q8_0.gguf new file mode 100644 index 0000000..26990cb --- /dev/null +++ b/Llama-3.2-3B-Blend.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ed25335c63489f15f76e7587f549d98733281c50d6c99bb0759931104c011c6 +size 3421900928 diff --git a/Llama-3.2-3B-Blend.f16.gguf b/Llama-3.2-3B-Blend.f16.gguf new file mode 100644 index 0000000..4d15669 --- /dev/null +++ b/Llama-3.2-3B-Blend.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:135ab35c95547c03fbb5e34b5c718d48ad9bcdd7134233a71823a3249f0b7b83 +size 6433689728 diff --git a/README.md b/README.md new file mode 100644 index 0000000..7ff0243 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: bunnycore/Llama-3.2-3B-Blend +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/bunnycore/Llama-3.2-3B-Blend + + +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-Blend-GGUF/resolve/main/Llama-3.2-3B-Blend.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Blend-GGUF/resolve/main/Llama-3.2-3B-Blend.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Blend-GGUF/resolve/main/Llama-3.2-3B-Blend.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Blend-GGUF/resolve/main/Llama-3.2-3B-Blend.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Blend-GGUF/resolve/main/Llama-3.2-3B-Blend.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Blend-GGUF/resolve/main/Llama-3.2-3B-Blend.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Blend-GGUF/resolve/main/Llama-3.2-3B-Blend.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Blend-GGUF/resolve/main/Llama-3.2-3B-Blend.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Blend-GGUF/resolve/main/Llama-3.2-3B-Blend.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Blend-GGUF/resolve/main/Llama-3.2-3B-Blend.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Blend-GGUF/resolve/main/Llama-3.2-3B-Blend.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Blend-GGUF/resolve/main/Llama-3.2-3B-Blend.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. + +