commit 340e3171ef0411b6920a65de853ca316ae5ac1ce Author: ModelHub XC Date: Wed Jun 3 11:21:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/presenton-llama-3.2-3b-1.0-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d908463 --- /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 +presenton-llama-3.2-3b-1.0.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +presenton-llama-3.2-3b-1.0.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +presenton-llama-3.2-3b-1.0.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +presenton-llama-3.2-3b-1.0.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +presenton-llama-3.2-3b-1.0.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +presenton-llama-3.2-3b-1.0.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +presenton-llama-3.2-3b-1.0.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +presenton-llama-3.2-3b-1.0.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +presenton-llama-3.2-3b-1.0.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +presenton-llama-3.2-3b-1.0.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +presenton-llama-3.2-3b-1.0.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +presenton-llama-3.2-3b-1.0.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..9eaf24b --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: surajbeston/presenton-llama-3.2-3b-1.0 +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +--- +## About + + + + + + + + + +static quants of https://huggingface.co/surajbeston/presenton-llama-3.2-3b-1.0 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#presenton-llama-3.2-3b-1.0-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/presenton-llama-3.2-3b-1.0-GGUF/resolve/main/presenton-llama-3.2-3b-1.0.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/presenton-llama-3.2-3b-1.0-GGUF/resolve/main/presenton-llama-3.2-3b-1.0.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/presenton-llama-3.2-3b-1.0-GGUF/resolve/main/presenton-llama-3.2-3b-1.0.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/presenton-llama-3.2-3b-1.0-GGUF/resolve/main/presenton-llama-3.2-3b-1.0.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/presenton-llama-3.2-3b-1.0-GGUF/resolve/main/presenton-llama-3.2-3b-1.0.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/presenton-llama-3.2-3b-1.0-GGUF/resolve/main/presenton-llama-3.2-3b-1.0.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/presenton-llama-3.2-3b-1.0-GGUF/resolve/main/presenton-llama-3.2-3b-1.0.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/presenton-llama-3.2-3b-1.0-GGUF/resolve/main/presenton-llama-3.2-3b-1.0.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/presenton-llama-3.2-3b-1.0-GGUF/resolve/main/presenton-llama-3.2-3b-1.0.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/presenton-llama-3.2-3b-1.0-GGUF/resolve/main/presenton-llama-3.2-3b-1.0.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/presenton-llama-3.2-3b-1.0-GGUF/resolve/main/presenton-llama-3.2-3b-1.0.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/presenton-llama-3.2-3b-1.0-GGUF/resolve/main/presenton-llama-3.2-3b-1.0.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/presenton-llama-3.2-3b-1.0.IQ4_XS.gguf b/presenton-llama-3.2-3b-1.0.IQ4_XS.gguf new file mode 100644 index 0000000..31f7156 --- /dev/null +++ b/presenton-llama-3.2-3b-1.0.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4111251673065222942461bca1b9525822e785a6173c8aa5d8844a7f0ba4c4cd +size 1840903424 diff --git a/presenton-llama-3.2-3b-1.0.Q2_K.gguf b/presenton-llama-3.2-3b-1.0.Q2_K.gguf new file mode 100644 index 0000000..be5a900 --- /dev/null +++ b/presenton-llama-3.2-3b-1.0.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f56fc4b2b41b4dd678b61d6d92973ee70fbb75668142329fcf571fdd6bfefd2 +size 1363932416 diff --git a/presenton-llama-3.2-3b-1.0.Q3_K_L.gguf b/presenton-llama-3.2-3b-1.0.Q3_K_L.gguf new file mode 100644 index 0000000..d3ac020 --- /dev/null +++ b/presenton-llama-3.2-3b-1.0.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d61850a6d63b8b34eb02ca338dae1b3d0a98a4e74c363e18c225105da363505c +size 1815344384 diff --git a/presenton-llama-3.2-3b-1.0.Q3_K_M.gguf b/presenton-llama-3.2-3b-1.0.Q3_K_M.gguf new file mode 100644 index 0000000..d723900 --- /dev/null +++ b/presenton-llama-3.2-3b-1.0.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94a35ec176a53e0d5cc85f1cb510d0038d6bdc15148118f763c5c75f12005caa +size 1687155968 diff --git a/presenton-llama-3.2-3b-1.0.Q3_K_S.gguf b/presenton-llama-3.2-3b-1.0.Q3_K_S.gguf new file mode 100644 index 0000000..5e546f6 --- /dev/null +++ b/presenton-llama-3.2-3b-1.0.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73824f2fe5e6b6464e8b6a0fa1ec1cc93635f6c40c42f4c5c96ff9ca6709b50c +size 1542845696 diff --git a/presenton-llama-3.2-3b-1.0.Q4_K_M.gguf b/presenton-llama-3.2-3b-1.0.Q4_K_M.gguf new file mode 100644 index 0000000..6afaecc --- /dev/null +++ b/presenton-llama-3.2-3b-1.0.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e272d6382b2f93eaf680bd750de093d246c9ddf66c3ee54425d296b9634ddf2c +size 2019374336 diff --git a/presenton-llama-3.2-3b-1.0.Q4_K_S.gguf b/presenton-llama-3.2-3b-1.0.Q4_K_S.gguf new file mode 100644 index 0000000..c28e897 --- /dev/null +++ b/presenton-llama-3.2-3b-1.0.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09d6b712ca4a31f6937e10ae256fe297103f43602eade668532d71fa13a4b44d +size 1928197376 diff --git a/presenton-llama-3.2-3b-1.0.Q5_K_M.gguf b/presenton-llama-3.2-3b-1.0.Q5_K_M.gguf new file mode 100644 index 0000000..0dc9b15 --- /dev/null +++ b/presenton-llama-3.2-3b-1.0.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3cb0590325c310f8e2d8286442f11fe50e1b2c6ac7c8a6c9fdf2deff25937417 +size 2322150656 diff --git a/presenton-llama-3.2-3b-1.0.Q5_K_S.gguf b/presenton-llama-3.2-3b-1.0.Q5_K_S.gguf new file mode 100644 index 0000000..4a3aac6 --- /dev/null +++ b/presenton-llama-3.2-3b-1.0.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42455a3b87538ede207742c178b0a92857f5d6467256f1774a4c4cc85a9fa041 +size 2269508864 diff --git a/presenton-llama-3.2-3b-1.0.Q6_K.gguf b/presenton-llama-3.2-3b-1.0.Q6_K.gguf new file mode 100644 index 0000000..255aeca --- /dev/null +++ b/presenton-llama-3.2-3b-1.0.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7ff0afe0bd44af66a2a58b305238e2d7c5d943e4cf0777374dd36e609430def +size 2643850496 diff --git a/presenton-llama-3.2-3b-1.0.Q8_0.gguf b/presenton-llama-3.2-3b-1.0.Q8_0.gguf new file mode 100644 index 0000000..68fe8bd --- /dev/null +++ b/presenton-llama-3.2-3b-1.0.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77a68ea8d989391315a2221c62d1e5946fba98e0493445adc6631519eb9f5673 +size 3421895936 diff --git a/presenton-llama-3.2-3b-1.0.f16.gguf b/presenton-llama-3.2-3b-1.0.f16.gguf new file mode 100644 index 0000000..b434e52 --- /dev/null +++ b/presenton-llama-3.2-3b-1.0.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef4fb9be14fca53960f10867cee9a0a95c7814a8477d3245c60ad9334a45f939 +size 6433684736