commit d5f27d61028dda4862c77f9bb5be6731fd43abe9 Author: ModelHub XC Date: Sun Sep 20 03:22:16 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/granite-4.0-h-3b-ar-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..73c547e --- /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 +granite-4.0-h-3b-ar.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +granite-4.0-h-3b-ar.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +granite-4.0-h-3b-ar.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +granite-4.0-h-3b-ar.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +granite-4.0-h-3b-ar.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +granite-4.0-h-3b-ar.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +granite-4.0-h-3b-ar.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +granite-4.0-h-3b-ar.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +granite-4.0-h-3b-ar.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +granite-4.0-h-3b-ar.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +granite-4.0-h-3b-ar.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +granite-4.0-h-3b-ar.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..99e856b --- /dev/null +++ b/README.md @@ -0,0 +1,79 @@ +--- +base_model: ibm-research/granite-4.0-h-3b-ar +language: +- en +- ar +- acm +- apc +- ars +- ary +- arz +- afb +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/ibm-research/granite-4.0-h-3b-ar + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#granite-4.0-h-3b-ar-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/granite-4.0-h-3b-ar-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/granite-4.0-h-3b-ar-GGUF/resolve/main/granite-4.0-h-3b-ar.Q2_K.gguf) | Q2_K | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/granite-4.0-h-3b-ar-GGUF/resolve/main/granite-4.0-h-3b-ar.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/granite-4.0-h-3b-ar-GGUF/resolve/main/granite-4.0-h-3b-ar.Q3_K_M.gguf) | Q3_K_M | 1.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/granite-4.0-h-3b-ar-GGUF/resolve/main/granite-4.0-h-3b-ar.Q3_K_L.gguf) | Q3_K_L | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/granite-4.0-h-3b-ar-GGUF/resolve/main/granite-4.0-h-3b-ar.IQ4_XS.gguf) | IQ4_XS | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/granite-4.0-h-3b-ar-GGUF/resolve/main/granite-4.0-h-3b-ar.Q4_K_S.gguf) | Q4_K_S | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/granite-4.0-h-3b-ar-GGUF/resolve/main/granite-4.0-h-3b-ar.Q4_K_M.gguf) | Q4_K_M | 2.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/granite-4.0-h-3b-ar-GGUF/resolve/main/granite-4.0-h-3b-ar.Q5_K_S.gguf) | Q5_K_S | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/granite-4.0-h-3b-ar-GGUF/resolve/main/granite-4.0-h-3b-ar.Q5_K_M.gguf) | Q5_K_M | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/granite-4.0-h-3b-ar-GGUF/resolve/main/granite-4.0-h-3b-ar.Q6_K.gguf) | Q6_K | 2.9 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/granite-4.0-h-3b-ar-GGUF/resolve/main/granite-4.0-h-3b-ar.Q8_0.gguf) | Q8_0 | 3.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/granite-4.0-h-3b-ar-GGUF/resolve/main/granite-4.0-h-3b-ar.f16.gguf) | f16 | 6.9 | 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/granite-4.0-h-3b-ar.IQ4_XS.gguf b/granite-4.0-h-3b-ar.IQ4_XS.gguf new file mode 100644 index 0000000..5995ba8 --- /dev/null +++ b/granite-4.0-h-3b-ar.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aed21b17a8753424d9319416212830a565c220ca9ad667d331ce15eb649bde5e +size 1884532768 diff --git a/granite-4.0-h-3b-ar.Q2_K.gguf b/granite-4.0-h-3b-ar.Q2_K.gguf new file mode 100644 index 0000000..65bb98a --- /dev/null +++ b/granite-4.0-h-3b-ar.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8eb44f7c30a9b7cc05dd7c619dea7cd5c3f660c74352895d9fb5f485e153cc50 +size 1293684768 diff --git a/granite-4.0-h-3b-ar.Q3_K_L.gguf b/granite-4.0-h-3b-ar.Q3_K_L.gguf new file mode 100644 index 0000000..ec11254 --- /dev/null +++ b/granite-4.0-h-3b-ar.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ac776f37382d826243ad09d221da05853a274f3e3af1dc0f22eb52e5ce0e416 +size 1725833248 diff --git a/granite-4.0-h-3b-ar.Q3_K_M.gguf b/granite-4.0-h-3b-ar.Q3_K_M.gguf new file mode 100644 index 0000000..6e393f0 --- /dev/null +++ b/granite-4.0-h-3b-ar.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:159697e7465ddfe04c0ee32da2c36198a2f18676ef947cbe23575a038bd426ee +size 1643782176 diff --git a/granite-4.0-h-3b-ar.Q3_K_S.gguf b/granite-4.0-h-3b-ar.Q3_K_S.gguf new file mode 100644 index 0000000..40ca8ee --- /dev/null +++ b/granite-4.0-h-3b-ar.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6121626b4aa56f1dbf0f645f437f7739edeee45cb4194c90336e08938bb1927a +size 1547411488 diff --git a/granite-4.0-h-3b-ar.Q4_K_M.gguf b/granite-4.0-h-3b-ar.Q4_K_M.gguf new file mode 100644 index 0000000..544ccb7 --- /dev/null +++ b/granite-4.0-h-3b-ar.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54b17f6d0dcfb3e8d9b5d98af050e1aa6d1e64d4f5cd167d506230aa7ddfeeb7 +size 2058170400 diff --git a/granite-4.0-h-3b-ar.Q4_K_S.gguf b/granite-4.0-h-3b-ar.Q4_K_S.gguf new file mode 100644 index 0000000..3615808 --- /dev/null +++ b/granite-4.0-h-3b-ar.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ddab2aa6db41a0082a7e747c3197d64a5f8b1845eaaf4b6a36608aa261455a1 +size 1982132256 diff --git a/granite-4.0-h-3b-ar.Q5_K_M.gguf b/granite-4.0-h-3b-ar.Q5_K_M.gguf new file mode 100644 index 0000000..c9ade17 --- /dev/null +++ b/granite-4.0-h-3b-ar.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eed2a4c9797d69905ba8299f513c77b104f6d12a86f9f2b6f8841bffdee4aba9 +size 2414751776 diff --git a/granite-4.0-h-3b-ar.Q5_K_S.gguf b/granite-4.0-h-3b-ar.Q5_K_S.gguf new file mode 100644 index 0000000..2d0cb03 --- /dev/null +++ b/granite-4.0-h-3b-ar.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5910588b97e9f0df765a67cf69facb716655e37b9f60a2dafec7ddfe837f7a9 +size 2369908768 diff --git a/granite-4.0-h-3b-ar.Q6_K.gguf b/granite-4.0-h-3b-ar.Q6_K.gguf new file mode 100644 index 0000000..e7d70a4 --- /dev/null +++ b/granite-4.0-h-3b-ar.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d07ec357408fd00eaffb12c1e280096778bd6bf7f3f9a469ccf5e5a59c8648a +size 2793619488 diff --git a/granite-4.0-h-3b-ar.Q8_0.gguf b/granite-4.0-h-3b-ar.Q8_0.gguf new file mode 100644 index 0000000..e740103 --- /dev/null +++ b/granite-4.0-h-3b-ar.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc6e703aacc32c21e30452cff460ec1d08ea8da9ea10200a2f02c5c1e602286c +size 3616043040 diff --git a/granite-4.0-h-3b-ar.f16.gguf b/granite-4.0-h-3b-ar.f16.gguf new file mode 100644 index 0000000..ff3563b --- /dev/null +++ b/granite-4.0-h-3b-ar.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18ac784c77fa08a80dc7ed96d57d3dcf39e9df2fa0204a1b9e222fb63eb716e2 +size 6799618080