commit 5328c949d483c42ca9157e20e5edb322a1ecb5e0 Author: ModelHub XC Date: Mon Aug 24 11:47:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/grabbe-ai-llama-3.2-3b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..9cfce25 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.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 +grabbe-ai-llama-3.2-3b.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +grabbe-ai-llama-3.2-3b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +grabbe-ai-llama-3.2-3b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +grabbe-ai-llama-3.2-3b.f16.gguf filter=lfs diff=lfs merge=lfs -text +grabbe-ai-llama-3.2-3b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +grabbe-ai-llama-3.2-3b.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +grabbe-ai-llama-3.2-3b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +grabbe-ai-llama-3.2-3b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +grabbe-ai-llama-3.2-3b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +grabbe-ai-llama-3.2-3b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +grabbe-ai-llama-3.2-3b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +grabbe-ai-llama-3.2-3b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +grabbe-ai-llama-3.2-3b.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +grabbe-ai-llama-3.2-3b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +grabbe-ai-llama-3.2-3b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..5ef99d1 --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +base_model: grabbe-gymnasium-detmold/grabbe-ai-llama-3.2-3b +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- unsloth +--- +## About + + + + + + +static quants of https://huggingface.co/grabbe-gymnasium-detmold/grabbe-ai-llama-3.2-3b + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/grabbe-ai-llama-3.2-3b-i1-GGUF +## 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/grabbe-ai-llama-3.2-3b-GGUF/resolve/main/grabbe-ai-llama-3.2-3b.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/grabbe-ai-llama-3.2-3b-GGUF/resolve/main/grabbe-ai-llama-3.2-3b.IQ3_XS.gguf) | IQ3_XS | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/grabbe-ai-llama-3.2-3b-GGUF/resolve/main/grabbe-ai-llama-3.2-3b.IQ3_S.gguf) | IQ3_S | 1.6 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/grabbe-ai-llama-3.2-3b-GGUF/resolve/main/grabbe-ai-llama-3.2-3b.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/grabbe-ai-llama-3.2-3b-GGUF/resolve/main/grabbe-ai-llama-3.2-3b.IQ3_M.gguf) | IQ3_M | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/grabbe-ai-llama-3.2-3b-GGUF/resolve/main/grabbe-ai-llama-3.2-3b.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/grabbe-ai-llama-3.2-3b-GGUF/resolve/main/grabbe-ai-llama-3.2-3b.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/grabbe-ai-llama-3.2-3b-GGUF/resolve/main/grabbe-ai-llama-3.2-3b.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/grabbe-ai-llama-3.2-3b-GGUF/resolve/main/grabbe-ai-llama-3.2-3b.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/grabbe-ai-llama-3.2-3b-GGUF/resolve/main/grabbe-ai-llama-3.2-3b.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/grabbe-ai-llama-3.2-3b-GGUF/resolve/main/grabbe-ai-llama-3.2-3b.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/grabbe-ai-llama-3.2-3b-GGUF/resolve/main/grabbe-ai-llama-3.2-3b.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/grabbe-ai-llama-3.2-3b-GGUF/resolve/main/grabbe-ai-llama-3.2-3b.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/grabbe-ai-llama-3.2-3b-GGUF/resolve/main/grabbe-ai-llama-3.2-3b.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/grabbe-ai-llama-3.2-3b-GGUF/resolve/main/grabbe-ai-llama-3.2-3b.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. + + diff --git a/grabbe-ai-llama-3.2-3b.IQ3_M.gguf b/grabbe-ai-llama-3.2-3b.IQ3_M.gguf new file mode 100644 index 0000000..07fb62a --- /dev/null +++ b/grabbe-ai-llama-3.2-3b.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ce6268747be84fedb03f660b44cf85ca265776863fbabfa88b83d18ca0a2404 +size 1599664960 diff --git a/grabbe-ai-llama-3.2-3b.IQ3_S.gguf b/grabbe-ai-llama-3.2-3b.IQ3_S.gguf new file mode 100644 index 0000000..38cdb73 --- /dev/null +++ b/grabbe-ai-llama-3.2-3b.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f8d61e454c614053a15c920d1fa9a35311020f6c0a05632d65ec3684524a997 +size 1542845248 diff --git a/grabbe-ai-llama-3.2-3b.IQ3_XS.gguf b/grabbe-ai-llama-3.2-3b.IQ3_XS.gguf new file mode 100644 index 0000000..677e1e5 --- /dev/null +++ b/grabbe-ai-llama-3.2-3b.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:599b905753c3f609ca701aae6425d4ee4ea2dfb58f880f89a9ad191bb6f340b8 +size 1476784960 diff --git a/grabbe-ai-llama-3.2-3b.IQ4_XS.gguf b/grabbe-ai-llama-3.2-3b.IQ4_XS.gguf new file mode 100644 index 0000000..65fbc7b --- /dev/null +++ b/grabbe-ai-llama-3.2-3b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a847251101ff03c6ec8ed0c5b620a537b24e5517e29fdfddc5cc5fb316404c05 +size 1840902976 diff --git a/grabbe-ai-llama-3.2-3b.Q2_K.gguf b/grabbe-ai-llama-3.2-3b.Q2_K.gguf new file mode 100644 index 0000000..04f2b78 --- /dev/null +++ b/grabbe-ai-llama-3.2-3b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c4af341ab7a3e4331ab063038a2d99ef822111b0b4281537fbcaae5af66c5fd +size 1363931968 diff --git a/grabbe-ai-llama-3.2-3b.Q3_K_L.gguf b/grabbe-ai-llama-3.2-3b.Q3_K_L.gguf new file mode 100644 index 0000000..8c812aa --- /dev/null +++ b/grabbe-ai-llama-3.2-3b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb649e02c5f5ce3144a2b62656389fa929db1e836b61d3b07acfae1790e675c4 +size 1815343936 diff --git a/grabbe-ai-llama-3.2-3b.Q3_K_M.gguf b/grabbe-ai-llama-3.2-3b.Q3_K_M.gguf new file mode 100644 index 0000000..3c397c6 --- /dev/null +++ b/grabbe-ai-llama-3.2-3b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca76a7d4e6572b29faede83cf946abd30beb5b9fef2960e36300beac6bcd7174 +size 1687155520 diff --git a/grabbe-ai-llama-3.2-3b.Q3_K_S.gguf b/grabbe-ai-llama-3.2-3b.Q3_K_S.gguf new file mode 100644 index 0000000..2028e3a --- /dev/null +++ b/grabbe-ai-llama-3.2-3b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80b0e35726cf70843c5f2790e5385c41179af1d0e8561d730e1e30d57b0bafd5 +size 1542845248 diff --git a/grabbe-ai-llama-3.2-3b.Q4_K_M.gguf b/grabbe-ai-llama-3.2-3b.Q4_K_M.gguf new file mode 100644 index 0000000..dfa4d7e --- /dev/null +++ b/grabbe-ai-llama-3.2-3b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b96f6ababa1f15f31f3d6f04330457bca525ff61f8dae6015873815af3f45933 +size 2019373888 diff --git a/grabbe-ai-llama-3.2-3b.Q4_K_S.gguf b/grabbe-ai-llama-3.2-3b.Q4_K_S.gguf new file mode 100644 index 0000000..16db95d --- /dev/null +++ b/grabbe-ai-llama-3.2-3b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc697fa68e1ac1ee90140a7db8f7bda649507ae0c3713e5b6c4c4ef4e99bc699 +size 1928196928 diff --git a/grabbe-ai-llama-3.2-3b.Q5_K_M.gguf b/grabbe-ai-llama-3.2-3b.Q5_K_M.gguf new file mode 100644 index 0000000..fed2f75 --- /dev/null +++ b/grabbe-ai-llama-3.2-3b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ace3bfab05025fb66e58e418b0d55f6d1747777d0d893c6dea3034fedfa462e4 +size 2322150208 diff --git a/grabbe-ai-llama-3.2-3b.Q5_K_S.gguf b/grabbe-ai-llama-3.2-3b.Q5_K_S.gguf new file mode 100644 index 0000000..fbac5e8 --- /dev/null +++ b/grabbe-ai-llama-3.2-3b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e01c7d3709df0b0197eff30d7113b0dafbde3b57f2ff444615c8b3bc535eec84 +size 2269508416 diff --git a/grabbe-ai-llama-3.2-3b.Q6_K.gguf b/grabbe-ai-llama-3.2-3b.Q6_K.gguf new file mode 100644 index 0000000..08334f2 --- /dev/null +++ b/grabbe-ai-llama-3.2-3b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9344e7c6c075cf51aba6d126b403ee9586c9c664c2fb82ceed0247414be678e +size 2643850048 diff --git a/grabbe-ai-llama-3.2-3b.Q8_0.gguf b/grabbe-ai-llama-3.2-3b.Q8_0.gguf new file mode 100644 index 0000000..ab4af95 --- /dev/null +++ b/grabbe-ai-llama-3.2-3b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b87c53816739058769c6c8a8f8e13c7cade7f1be01cf8438b23123ee8e1d2963 +size 3421895488 diff --git a/grabbe-ai-llama-3.2-3b.f16.gguf b/grabbe-ai-llama-3.2-3b.f16.gguf new file mode 100644 index 0000000..549fc1c --- /dev/null +++ b/grabbe-ai-llama-3.2-3b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43c9b84e39ccea781684d88b58a8d3418db575c242ca1ded06e933e5e57ecc29 +size 6433684288