commit 55c4e6066ff9201bdd6bb1a31c54ff6ba17562ea Author: ModelHub XC Date: Fri Jul 24 02:55:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.2-3B-Stock-v1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..b894788 --- /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-Stock-v1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Stock-v1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Stock-v1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Stock-v1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Stock-v1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Stock-v1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Stock-v1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Stock-v1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Stock-v1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Stock-v1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Stock-v1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Stock-v1.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.2-3B-Stock-v1.IQ4_XS.gguf b/Llama-3.2-3B-Stock-v1.IQ4_XS.gguf new file mode 100644 index 0000000..dcf6a74 --- /dev/null +++ b/Llama-3.2-3B-Stock-v1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:085a5c2073c6a468d6457fa5ee3efd58d4d0f934549f0ff17db8f9e847597f9e +size 1840908288 diff --git a/Llama-3.2-3B-Stock-v1.Q2_K.gguf b/Llama-3.2-3B-Stock-v1.Q2_K.gguf new file mode 100644 index 0000000..c5b273c --- /dev/null +++ b/Llama-3.2-3B-Stock-v1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e30159631d27b340240b4af351c37f020a5054fc74f5bdfee214f42678a8fd6 +size 1363937280 diff --git a/Llama-3.2-3B-Stock-v1.Q3_K_L.gguf b/Llama-3.2-3B-Stock-v1.Q3_K_L.gguf new file mode 100644 index 0000000..e0d8152 --- /dev/null +++ b/Llama-3.2-3B-Stock-v1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:864bd91e1e33709e1f5d5c194ca15d4135972bd6f32480ec605a88f7a948142d +size 1815349248 diff --git a/Llama-3.2-3B-Stock-v1.Q3_K_M.gguf b/Llama-3.2-3B-Stock-v1.Q3_K_M.gguf new file mode 100644 index 0000000..c0dfcc6 --- /dev/null +++ b/Llama-3.2-3B-Stock-v1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43acf2533992de6d73550b5416d984f86e3d65fc7409c6af237bf579e1d65672 +size 1687160832 diff --git a/Llama-3.2-3B-Stock-v1.Q3_K_S.gguf b/Llama-3.2-3B-Stock-v1.Q3_K_S.gguf new file mode 100644 index 0000000..7121867 --- /dev/null +++ b/Llama-3.2-3B-Stock-v1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f292614326708596d8be22d72149ad632cf0757e094f0489a5b053f046cc5ecc +size 1542850560 diff --git a/Llama-3.2-3B-Stock-v1.Q4_K_M.gguf b/Llama-3.2-3B-Stock-v1.Q4_K_M.gguf new file mode 100644 index 0000000..87f7872 --- /dev/null +++ b/Llama-3.2-3B-Stock-v1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd033ae823d74b595ee79905c0d0f69ac42d1c95bed17f131333343ae06f7873 +size 2019379200 diff --git a/Llama-3.2-3B-Stock-v1.Q4_K_S.gguf b/Llama-3.2-3B-Stock-v1.Q4_K_S.gguf new file mode 100644 index 0000000..ed16a49 --- /dev/null +++ b/Llama-3.2-3B-Stock-v1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f089893583030f72050f63ee9ac18ccb81addb3c1d46735835d5215c58b0086 +size 1928202240 diff --git a/Llama-3.2-3B-Stock-v1.Q5_K_M.gguf b/Llama-3.2-3B-Stock-v1.Q5_K_M.gguf new file mode 100644 index 0000000..170f3d8 --- /dev/null +++ b/Llama-3.2-3B-Stock-v1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7217797096df0ee4efcaef5b00ba63ba2c2fb2917b860d89a5570d1b2c36de0e +size 2322155520 diff --git a/Llama-3.2-3B-Stock-v1.Q5_K_S.gguf b/Llama-3.2-3B-Stock-v1.Q5_K_S.gguf new file mode 100644 index 0000000..d026483 --- /dev/null +++ b/Llama-3.2-3B-Stock-v1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26f6448370196020c72be299ba3d85791d28c411cd4f7e1be46acbbffada2620 +size 2269513728 diff --git a/Llama-3.2-3B-Stock-v1.Q6_K.gguf b/Llama-3.2-3B-Stock-v1.Q6_K.gguf new file mode 100644 index 0000000..6fed1f5 --- /dev/null +++ b/Llama-3.2-3B-Stock-v1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2aeba0028354dc59f8b6891686f9b31c0c216a1dd26062c57c4ffec1538052fb +size 2643855360 diff --git a/Llama-3.2-3B-Stock-v1.Q8_0.gguf b/Llama-3.2-3B-Stock-v1.Q8_0.gguf new file mode 100644 index 0000000..6bae2a0 --- /dev/null +++ b/Llama-3.2-3B-Stock-v1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c864f00e6c5ce874d83ea8a6a2d4d6e418048afdfb84e762e8baa37df61bdaf6 +size 3421900800 diff --git a/Llama-3.2-3B-Stock-v1.f16.gguf b/Llama-3.2-3B-Stock-v1.f16.gguf new file mode 100644 index 0000000..8bc0229 --- /dev/null +++ b/Llama-3.2-3B-Stock-v1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4d5c741a1d7d29bf42b94d9e60b438152c0fe43b9df6b5350ee6d88b415eeb5 +size 6433689600 diff --git a/README.md b/README.md new file mode 100644 index 0000000..d408661 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: bunnycore/Llama-3.2-3B-Stock-v1 +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/bunnycore/Llama-3.2-3B-Stock-v1 + + +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-Stock-v1-GGUF/resolve/main/Llama-3.2-3B-Stock-v1.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Stock-v1-GGUF/resolve/main/Llama-3.2-3B-Stock-v1.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Stock-v1-GGUF/resolve/main/Llama-3.2-3B-Stock-v1.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Stock-v1-GGUF/resolve/main/Llama-3.2-3B-Stock-v1.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Stock-v1-GGUF/resolve/main/Llama-3.2-3B-Stock-v1.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Stock-v1-GGUF/resolve/main/Llama-3.2-3B-Stock-v1.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Stock-v1-GGUF/resolve/main/Llama-3.2-3B-Stock-v1.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Stock-v1-GGUF/resolve/main/Llama-3.2-3B-Stock-v1.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Stock-v1-GGUF/resolve/main/Llama-3.2-3B-Stock-v1.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Stock-v1-GGUF/resolve/main/Llama-3.2-3B-Stock-v1.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Stock-v1-GGUF/resolve/main/Llama-3.2-3B-Stock-v1.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Stock-v1-GGUF/resolve/main/Llama-3.2-3B-Stock-v1.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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + +