commit 9d51ff55b1969c280f2a8ddc29a82652db894509 Author: ModelHub XC Date: Thu Jun 18 10:20:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama3.2-typhoon2-3b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a04a246 --- /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 +llama3.2-typhoon2-3b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama3.2-typhoon2-3b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama3.2-typhoon2-3b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama3.2-typhoon2-3b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3.2-typhoon2-3b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3.2-typhoon2-3b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3.2-typhoon2-3b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3.2-typhoon2-3b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3.2-typhoon2-3b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3.2-typhoon2-3b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama3.2-typhoon2-3b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama3.2-typhoon2-3b.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..d55aed3 --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: typhoon-ai/llama3.2-typhoon2-3b +language: +- en +library_name: transformers +license: llama3.2 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/typhoon-ai/llama3.2-typhoon2-3b + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#llama3.2-typhoon2-3b-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/llama3.2-typhoon2-3b-GGUF/resolve/main/llama3.2-typhoon2-3b.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.2-typhoon2-3b-GGUF/resolve/main/llama3.2-typhoon2-3b.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.2-typhoon2-3b-GGUF/resolve/main/llama3.2-typhoon2-3b.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama3.2-typhoon2-3b-GGUF/resolve/main/llama3.2-typhoon2-3b.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.2-typhoon2-3b-GGUF/resolve/main/llama3.2-typhoon2-3b.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.2-typhoon2-3b-GGUF/resolve/main/llama3.2-typhoon2-3b.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama3.2-typhoon2-3b-GGUF/resolve/main/llama3.2-typhoon2-3b.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama3.2-typhoon2-3b-GGUF/resolve/main/llama3.2-typhoon2-3b.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.2-typhoon2-3b-GGUF/resolve/main/llama3.2-typhoon2-3b.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.2-typhoon2-3b-GGUF/resolve/main/llama3.2-typhoon2-3b.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama3.2-typhoon2-3b-GGUF/resolve/main/llama3.2-typhoon2-3b.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama3.2-typhoon2-3b-GGUF/resolve/main/llama3.2-typhoon2-3b.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. + + diff --git a/llama3.2-typhoon2-3b.IQ4_XS.gguf b/llama3.2-typhoon2-3b.IQ4_XS.gguf new file mode 100644 index 0000000..814f62e --- /dev/null +++ b/llama3.2-typhoon2-3b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9f46eb3e3f9488c3fd8cfbf5325a7af2f31e45fddfbaf1c2d84b1d452722104 +size 1840906720 diff --git a/llama3.2-typhoon2-3b.Q2_K.gguf b/llama3.2-typhoon2-3b.Q2_K.gguf new file mode 100644 index 0000000..94786cc --- /dev/null +++ b/llama3.2-typhoon2-3b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f5db176434b4afbc7d9c7f3fa1fa5a7e5230eceac51afd1320928d0a2ea9d7d +size 1363935712 diff --git a/llama3.2-typhoon2-3b.Q3_K_L.gguf b/llama3.2-typhoon2-3b.Q3_K_L.gguf new file mode 100644 index 0000000..658a829 --- /dev/null +++ b/llama3.2-typhoon2-3b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50b6f990c12c2e1c6ff8a65bf6361e971c18947372eaa66328f8f5a26a56b4ac +size 1815347680 diff --git a/llama3.2-typhoon2-3b.Q3_K_M.gguf b/llama3.2-typhoon2-3b.Q3_K_M.gguf new file mode 100644 index 0000000..bef1817 --- /dev/null +++ b/llama3.2-typhoon2-3b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b8250e5e683d1ff75bc45424aa594e38e98934fa1f76c9987973ada59ee9956 +size 1687159264 diff --git a/llama3.2-typhoon2-3b.Q3_K_S.gguf b/llama3.2-typhoon2-3b.Q3_K_S.gguf new file mode 100644 index 0000000..6527b99 --- /dev/null +++ b/llama3.2-typhoon2-3b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:472f8ae60c0bc2b228f27862ea997efafec121e26b1bcbfb29c1286272085f31 +size 1542848992 diff --git a/llama3.2-typhoon2-3b.Q4_K_M.gguf b/llama3.2-typhoon2-3b.Q4_K_M.gguf new file mode 100644 index 0000000..36d17c9 --- /dev/null +++ b/llama3.2-typhoon2-3b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:582d8041bf23ce369cdd87197a9f33e953f325189f603f057c8bef30bb01d854 +size 2019377632 diff --git a/llama3.2-typhoon2-3b.Q4_K_S.gguf b/llama3.2-typhoon2-3b.Q4_K_S.gguf new file mode 100644 index 0000000..c1c23e4 --- /dev/null +++ b/llama3.2-typhoon2-3b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:271acd57365955ab46a46a33874e9dbc35deac8b078a5fce13bd0a247e89a463 +size 1928200672 diff --git a/llama3.2-typhoon2-3b.Q5_K_M.gguf b/llama3.2-typhoon2-3b.Q5_K_M.gguf new file mode 100644 index 0000000..e8a5e73 --- /dev/null +++ b/llama3.2-typhoon2-3b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63ae19a58b6479b5513716f61eb460f8c35f9b40502267166d254942bc0bbca1 +size 2322153952 diff --git a/llama3.2-typhoon2-3b.Q5_K_S.gguf b/llama3.2-typhoon2-3b.Q5_K_S.gguf new file mode 100644 index 0000000..e662d65 --- /dev/null +++ b/llama3.2-typhoon2-3b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0b56a0fcc611a06596ad999bb7970dc121249901134a0c33f7d4e9ed7fb4336 +size 2269512160 diff --git a/llama3.2-typhoon2-3b.Q6_K.gguf b/llama3.2-typhoon2-3b.Q6_K.gguf new file mode 100644 index 0000000..10f9d1c --- /dev/null +++ b/llama3.2-typhoon2-3b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32e11fa5cffc8b734f80e846dd2c8f62d9cd88fde729304e8b2428f08aef2c45 +size 2643853792 diff --git a/llama3.2-typhoon2-3b.Q8_0.gguf b/llama3.2-typhoon2-3b.Q8_0.gguf new file mode 100644 index 0000000..9347c0c --- /dev/null +++ b/llama3.2-typhoon2-3b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41b814780ee94f7323d46d7abac1ff857cd0323a07ef061e09a1082e239cf0a6 +size 3421899232 diff --git a/llama3.2-typhoon2-3b.f16.gguf b/llama3.2-typhoon2-3b.f16.gguf new file mode 100644 index 0000000..f4717b8 --- /dev/null +++ b/llama3.2-typhoon2-3b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b03ea32b3810585da5483cd18ecd2272a0853a8b47b999790dd48b7f9a73906 +size 6433688032