commit a9020a7cdb0845d55cb8aa9dae2768a8949ec930 Author: ModelHub XC Date: Tue Jul 7 21:21:11 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Phoenix-Ultra-Llama3.2-3B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e8ff7ea --- /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 +Phoenix-Ultra-Llama3.2-3B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Phoenix-Ultra-Llama3.2-3B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Phoenix-Ultra-Llama3.2-3B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Phoenix-Ultra-Llama3.2-3B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Phoenix-Ultra-Llama3.2-3B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Phoenix-Ultra-Llama3.2-3B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Phoenix-Ultra-Llama3.2-3B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Phoenix-Ultra-Llama3.2-3B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Phoenix-Ultra-Llama3.2-3B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Phoenix-Ultra-Llama3.2-3B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Phoenix-Ultra-Llama3.2-3B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Phoenix-Ultra-Llama3.2-3B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Phoenix-Ultra-Llama3.2-3B.IQ4_XS.gguf b/Phoenix-Ultra-Llama3.2-3B.IQ4_XS.gguf new file mode 100644 index 0000000..a330b7c --- /dev/null +++ b/Phoenix-Ultra-Llama3.2-3B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4ac00191bdc3bbb2c0b97c6cf6336bf99186842056121797a334d0acef32ad8 +size 1840906560 diff --git a/Phoenix-Ultra-Llama3.2-3B.Q2_K.gguf b/Phoenix-Ultra-Llama3.2-3B.Q2_K.gguf new file mode 100644 index 0000000..6abaf2b --- /dev/null +++ b/Phoenix-Ultra-Llama3.2-3B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e5f2df518fad65d224033b826bd3b4ea025bcaab8bbbe0c16829ef79880cfe8 +size 1363935552 diff --git a/Phoenix-Ultra-Llama3.2-3B.Q3_K_L.gguf b/Phoenix-Ultra-Llama3.2-3B.Q3_K_L.gguf new file mode 100644 index 0000000..07f4077 --- /dev/null +++ b/Phoenix-Ultra-Llama3.2-3B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34696fcbcea745e374706eb22996f090f4d739e183676fce8ad9bc9141f62f17 +size 1815347520 diff --git a/Phoenix-Ultra-Llama3.2-3B.Q3_K_M.gguf b/Phoenix-Ultra-Llama3.2-3B.Q3_K_M.gguf new file mode 100644 index 0000000..4199b2f --- /dev/null +++ b/Phoenix-Ultra-Llama3.2-3B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:281e3a01b34938b5c772c40fc3db83e9a55a45662d36b284239b29c570bff317 +size 1687159104 diff --git a/Phoenix-Ultra-Llama3.2-3B.Q3_K_S.gguf b/Phoenix-Ultra-Llama3.2-3B.Q3_K_S.gguf new file mode 100644 index 0000000..41bb063 --- /dev/null +++ b/Phoenix-Ultra-Llama3.2-3B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f0656e58205990685c5c6d5cd651403997275fdbeb5c1043a25f292fbc71cc1 +size 1542848832 diff --git a/Phoenix-Ultra-Llama3.2-3B.Q4_K_M.gguf b/Phoenix-Ultra-Llama3.2-3B.Q4_K_M.gguf new file mode 100644 index 0000000..ab14e43 --- /dev/null +++ b/Phoenix-Ultra-Llama3.2-3B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ece37fac125c8bf8cf687544f9383fe838dc49cde3255cdbce069d229aba5c61 +size 2019377472 diff --git a/Phoenix-Ultra-Llama3.2-3B.Q4_K_S.gguf b/Phoenix-Ultra-Llama3.2-3B.Q4_K_S.gguf new file mode 100644 index 0000000..7ccafca --- /dev/null +++ b/Phoenix-Ultra-Llama3.2-3B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18abb9ba38e4cc92f1030cee62153ac2538040ce6c471090e45b91da833d7af9 +size 1928200512 diff --git a/Phoenix-Ultra-Llama3.2-3B.Q5_K_M.gguf b/Phoenix-Ultra-Llama3.2-3B.Q5_K_M.gguf new file mode 100644 index 0000000..c954696 --- /dev/null +++ b/Phoenix-Ultra-Llama3.2-3B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ef658716c88e6f353ad3e24ccf7980d986bc1b41c0df6a1c9b12b0bb72fa09c +size 2322153792 diff --git a/Phoenix-Ultra-Llama3.2-3B.Q5_K_S.gguf b/Phoenix-Ultra-Llama3.2-3B.Q5_K_S.gguf new file mode 100644 index 0000000..e91fc2b --- /dev/null +++ b/Phoenix-Ultra-Llama3.2-3B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16948f2e0a9962bc96e119cb250e840d83e341a5b3345dc7cc848b9da209b14f +size 2269512000 diff --git a/Phoenix-Ultra-Llama3.2-3B.Q6_K.gguf b/Phoenix-Ultra-Llama3.2-3B.Q6_K.gguf new file mode 100644 index 0000000..351811a --- /dev/null +++ b/Phoenix-Ultra-Llama3.2-3B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:928ba65ae4eb52d39a2c0b9e0cfa652d33d9f7f6bc1a8c571720690fc90c90fb +size 2643853632 diff --git a/Phoenix-Ultra-Llama3.2-3B.Q8_0.gguf b/Phoenix-Ultra-Llama3.2-3B.Q8_0.gguf new file mode 100644 index 0000000..601f792 --- /dev/null +++ b/Phoenix-Ultra-Llama3.2-3B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33bfee56d7b779cef42bf5c1c4f3cd288871bf535587149f9e4bce6c390f105a +size 3421899072 diff --git a/Phoenix-Ultra-Llama3.2-3B.f16.gguf b/Phoenix-Ultra-Llama3.2-3B.f16.gguf new file mode 100644 index 0000000..74708cb --- /dev/null +++ b/Phoenix-Ultra-Llama3.2-3B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf42c5be68f54cf7c0a44d5ba6f412c44c72f0b65f3d74b95f8e860172f51479 +size 6433687872 diff --git a/README.md b/README.md new file mode 100644 index 0000000..2c5cd2f --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: MostafaHanafy/Phoenix-Ultra-Llama3.2-3B +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/MostafaHanafy/Phoenix-Ultra-Llama3.2-3B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Phoenix-Ultra-Llama3.2-3B-GGUF).*** + +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/Phoenix-Ultra-Llama3.2-3B-GGUF/resolve/main/Phoenix-Ultra-Llama3.2-3B.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Phoenix-Ultra-Llama3.2-3B-GGUF/resolve/main/Phoenix-Ultra-Llama3.2-3B.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Phoenix-Ultra-Llama3.2-3B-GGUF/resolve/main/Phoenix-Ultra-Llama3.2-3B.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Phoenix-Ultra-Llama3.2-3B-GGUF/resolve/main/Phoenix-Ultra-Llama3.2-3B.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Phoenix-Ultra-Llama3.2-3B-GGUF/resolve/main/Phoenix-Ultra-Llama3.2-3B.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Phoenix-Ultra-Llama3.2-3B-GGUF/resolve/main/Phoenix-Ultra-Llama3.2-3B.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Phoenix-Ultra-Llama3.2-3B-GGUF/resolve/main/Phoenix-Ultra-Llama3.2-3B.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Phoenix-Ultra-Llama3.2-3B-GGUF/resolve/main/Phoenix-Ultra-Llama3.2-3B.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Phoenix-Ultra-Llama3.2-3B-GGUF/resolve/main/Phoenix-Ultra-Llama3.2-3B.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Phoenix-Ultra-Llama3.2-3B-GGUF/resolve/main/Phoenix-Ultra-Llama3.2-3B.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Phoenix-Ultra-Llama3.2-3B-GGUF/resolve/main/Phoenix-Ultra-Llama3.2-3B.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Phoenix-Ultra-Llama3.2-3B-GGUF/resolve/main/Phoenix-Ultra-Llama3.2-3B.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. + +