commit 7125a42eb34495f2723d90b1db01317c8d568b65 Author: ModelHub XC Date: Tue Jun 16 20:57:21 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/granite-3.3-8b-base-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..767880c --- /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-3.3-8b-base.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.3-8b-base.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.3-8b-base.f16.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.3-8b-base.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.3-8b-base.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.3-8b-base.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.3-8b-base.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.3-8b-base.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.3-8b-base.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.3-8b-base.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.3-8b-base.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.3-8b-base.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..0c3edfb --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: ibm-granite/granite-3.3-8b-base +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- language +- granite-3.3 +--- +## About + + + + + + +static quants of https://huggingface.co/ibm-granite/granite-3.3-8b-base + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#granite-3.3-8b-base-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/granite-3.3-8b-base-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-3.3-8b-base-GGUF/resolve/main/granite-3.3-8b-base.Q2_K.gguf) | Q2_K | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/granite-3.3-8b-base-GGUF/resolve/main/granite-3.3-8b-base.Q3_K_S.gguf) | Q3_K_S | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/granite-3.3-8b-base-GGUF/resolve/main/granite-3.3-8b-base.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/granite-3.3-8b-base-GGUF/resolve/main/granite-3.3-8b-base.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/granite-3.3-8b-base-GGUF/resolve/main/granite-3.3-8b-base.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/granite-3.3-8b-base-GGUF/resolve/main/granite-3.3-8b-base.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/granite-3.3-8b-base-GGUF/resolve/main/granite-3.3-8b-base.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/granite-3.3-8b-base-GGUF/resolve/main/granite-3.3-8b-base.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/granite-3.3-8b-base-GGUF/resolve/main/granite-3.3-8b-base.Q5_K_M.gguf) | Q5_K_M | 5.9 | | +| [GGUF](https://huggingface.co/mradermacher/granite-3.3-8b-base-GGUF/resolve/main/granite-3.3-8b-base.Q6_K.gguf) | Q6_K | 6.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/granite-3.3-8b-base-GGUF/resolve/main/granite-3.3-8b-base.Q8_0.gguf) | Q8_0 | 8.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/granite-3.3-8b-base-GGUF/resolve/main/granite-3.3-8b-base.f16.gguf) | f16 | 16.4 | 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-3.3-8b-base.IQ4_XS.gguf b/granite-3.3-8b-base.IQ4_XS.gguf new file mode 100644 index 0000000..d5e9cca --- /dev/null +++ b/granite-3.3-8b-base.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89e354a5e8955490188937ea28123a4c62f09f2e48cfc69124d711337df1127d +size 4469019872 diff --git a/granite-3.3-8b-base.Q2_K.gguf b/granite-3.3-8b-base.Q2_K.gguf new file mode 100644 index 0000000..8430520 --- /dev/null +++ b/granite-3.3-8b-base.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ba6448738e5e881aa381948753940047c7d7a43462cb114c3e833691ecd7443 +size 3103577312 diff --git a/granite-3.3-8b-base.Q3_K_L.gguf b/granite-3.3-8b-base.Q3_K_L.gguf new file mode 100644 index 0000000..5f8d2b9 --- /dev/null +++ b/granite-3.3-8b-base.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81ec518d7699618e16e5a09733902c902c2c23209ff0e504172c089413e57014 +size 4349416672 diff --git a/granite-3.3-8b-base.Q3_K_M.gguf b/granite-3.3-8b-base.Q3_K_M.gguf new file mode 100644 index 0000000..0f84e50 --- /dev/null +++ b/granite-3.3-8b-base.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:645feaaed3a81d6c6f56c1ce3285953463c1920738a721977235f9624e2a85d1 +size 3996570848 diff --git a/granite-3.3-8b-base.Q3_K_S.gguf b/granite-3.3-8b-base.Q3_K_S.gguf new file mode 100644 index 0000000..9d45337 --- /dev/null +++ b/granite-3.3-8b-base.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2dfa140223ea582a3057505bac0011c6ff910c74ab977fcba6ce496ff5a9d5b8 +size 3592475872 diff --git a/granite-3.3-8b-base.Q4_K_M.gguf b/granite-3.3-8b-base.Q4_K_M.gguf new file mode 100644 index 0000000..bd65807 --- /dev/null +++ b/granite-3.3-8b-base.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37fc0f912dd621323c043c56ed7fa6c4e2c1a27492dd4a0707c86fda93a45397 +size 4942845152 diff --git a/granite-3.3-8b-base.Q4_K_S.gguf b/granite-3.3-8b-base.Q4_K_S.gguf new file mode 100644 index 0000000..3a15c42 --- /dev/null +++ b/granite-3.3-8b-base.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:734015efcc5691eef0bbf38192ffe3675d58deff4f0eebfa62900fe0e86b436d +size 4685747424 diff --git a/granite-3.3-8b-base.Q5_K_M.gguf b/granite-3.3-8b-base.Q5_K_M.gguf new file mode 100644 index 0000000..ebb98c8 --- /dev/null +++ b/granite-3.3-8b-base.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe06bf140bbc428dd244912cb157030015dd99aef17b8a724c0fd3b8d7e65f61 +size 5797434592 diff --git a/granite-3.3-8b-base.Q5_K_S.gguf b/granite-3.3-8b-base.Q5_K_S.gguf new file mode 100644 index 0000000..a5336a5 --- /dev/null +++ b/granite-3.3-8b-base.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:777ea0cd356bba3ecf0238af41edf52056aaabaf81ebe45d1610f87c48f066f8 +size 5647029472 diff --git a/granite-3.3-8b-base.Q6_K.gguf b/granite-3.3-8b-base.Q6_K.gguf new file mode 100644 index 0000000..eec411d --- /dev/null +++ b/granite-3.3-8b-base.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57685497134545e82253bda0e4585e30ee866786b3c10d7df432c9e41fdafe1b +size 6705435872 diff --git a/granite-3.3-8b-base.Q8_0.gguf b/granite-3.3-8b-base.Q8_0.gguf new file mode 100644 index 0000000..d2ab2d6 --- /dev/null +++ b/granite-3.3-8b-base.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba10764b40e7afb416f26f2db78f97ef4a074e28a57a58f431581704bf5950e5 +size 8684229856 diff --git a/granite-3.3-8b-base.f16.gguf b/granite-3.3-8b-base.f16.gguf new file mode 100644 index 0000000..fecc3d3 --- /dev/null +++ b/granite-3.3-8b-base.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c7bac5424521f2e6bb60073b4af4801325db454ad885f78ed35bf65cbde86e7 +size 16344077536