commit 9f77c2889f0278114f7dd5a57156169ef7fee750 Author: ModelHub XC Date: Tue Jul 21 07:22:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/granite-3.0-8b-base-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..455b025 --- /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-3.0-8b-base.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.0-8b-base.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.0-8b-base.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.0-8b-base.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.0-8b-base.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.0-8b-base.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.0-8b-base.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.0-8b-base.f16.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.0-8b-base.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.0-8b-base.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.0-8b-base.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.0-8b-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..c052a50 --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: ibm-granite/granite-3.0-8b-base +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- language +- granite-3.0 +--- +## About + + + + + + +static quants of https://huggingface.co/ibm-granite/granite-3.0-8b-base + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/granite-3.0-8b-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-3.0-8b-base-GGUF/resolve/main/granite-3.0-8b-base.Q2_K.gguf) | Q2_K | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/granite-3.0-8b-base-GGUF/resolve/main/granite-3.0-8b-base.Q3_K_S.gguf) | Q3_K_S | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/granite-3.0-8b-base-GGUF/resolve/main/granite-3.0-8b-base.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/granite-3.0-8b-base-GGUF/resolve/main/granite-3.0-8b-base.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/granite-3.0-8b-base-GGUF/resolve/main/granite-3.0-8b-base.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/granite-3.0-8b-base-GGUF/resolve/main/granite-3.0-8b-base.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/granite-3.0-8b-base-GGUF/resolve/main/granite-3.0-8b-base.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/granite-3.0-8b-base-GGUF/resolve/main/granite-3.0-8b-base.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/granite-3.0-8b-base-GGUF/resolve/main/granite-3.0-8b-base.Q5_K_M.gguf) | Q5_K_M | 5.9 | | +| [GGUF](https://huggingface.co/mradermacher/granite-3.0-8b-base-GGUF/resolve/main/granite-3.0-8b-base.Q6_K.gguf) | Q6_K | 6.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/granite-3.0-8b-base-GGUF/resolve/main/granite-3.0-8b-base.Q8_0.gguf) | Q8_0 | 8.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/granite-3.0-8b-base-GGUF/resolve/main/granite-3.0-8b-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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + + diff --git a/granite-3.0-8b-base.IQ4_XS.gguf b/granite-3.0-8b-base.IQ4_XS.gguf new file mode 100644 index 0000000..f0e547b --- /dev/null +++ b/granite-3.0-8b-base.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33828cda85085a017b7e21ef066c9119cb73641c8f3bef8cb26c97d41e85640e +size 4469019904 diff --git a/granite-3.0-8b-base.Q2_K.gguf b/granite-3.0-8b-base.Q2_K.gguf new file mode 100644 index 0000000..6d4ecf7 --- /dev/null +++ b/granite-3.0-8b-base.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e4e02f80fcfcf04784cf9b5c5de480f0c0a60b33c08cde265cd95fd7edbd43e +size 3103577344 diff --git a/granite-3.0-8b-base.Q3_K_L.gguf b/granite-3.0-8b-base.Q3_K_L.gguf new file mode 100644 index 0000000..a1b122f --- /dev/null +++ b/granite-3.0-8b-base.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9fd5dfbe55b89ac2641241fe0e7ea8d03f571d9d08ec6e33e8b91d699cadbba6 +size 4349416704 diff --git a/granite-3.0-8b-base.Q3_K_M.gguf b/granite-3.0-8b-base.Q3_K_M.gguf new file mode 100644 index 0000000..3f29d94 --- /dev/null +++ b/granite-3.0-8b-base.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0bb46f2bbd6af75f7ec228e9531e85868a2607d3557a8f7ac7548ccfac02dbc +size 3996570880 diff --git a/granite-3.0-8b-base.Q3_K_S.gguf b/granite-3.0-8b-base.Q3_K_S.gguf new file mode 100644 index 0000000..c3151ea --- /dev/null +++ b/granite-3.0-8b-base.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04b4a008a12cefa75ae4ddbfb789f7d86abfa25730605e9761b63175c7565e11 +size 3592475904 diff --git a/granite-3.0-8b-base.Q4_K_M.gguf b/granite-3.0-8b-base.Q4_K_M.gguf new file mode 100644 index 0000000..1ccba87 --- /dev/null +++ b/granite-3.0-8b-base.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12a4ecda0b3f751908970cc6b331e8db3970452e0119899740a3537002c1c0f3 +size 4942845184 diff --git a/granite-3.0-8b-base.Q4_K_S.gguf b/granite-3.0-8b-base.Q4_K_S.gguf new file mode 100644 index 0000000..4a569f7 --- /dev/null +++ b/granite-3.0-8b-base.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66ff13839373b28c6342f0c1b6f00b5dbe9290c9db1dc8423a90009e253a76e2 +size 4685747456 diff --git a/granite-3.0-8b-base.Q5_K_M.gguf b/granite-3.0-8b-base.Q5_K_M.gguf new file mode 100644 index 0000000..fd30f39 --- /dev/null +++ b/granite-3.0-8b-base.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7aad10fa0467591d0bfd6c761221fe032aba326c84d4aead8a6c78bb215bb118 +size 5797434624 diff --git a/granite-3.0-8b-base.Q5_K_S.gguf b/granite-3.0-8b-base.Q5_K_S.gguf new file mode 100644 index 0000000..400e65f --- /dev/null +++ b/granite-3.0-8b-base.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4e17af12da09ba69f8b9a94229911a7d7a8bf8d99f1b0b68da2e11ddbffa6d1 +size 5647029504 diff --git a/granite-3.0-8b-base.Q6_K.gguf b/granite-3.0-8b-base.Q6_K.gguf new file mode 100644 index 0000000..0322793 --- /dev/null +++ b/granite-3.0-8b-base.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eaa3052afbee2eff7394918b44c80ca6c085de55fb626310569266d32acc3f37 +size 6705435904 diff --git a/granite-3.0-8b-base.Q8_0.gguf b/granite-3.0-8b-base.Q8_0.gguf new file mode 100644 index 0000000..183f258 --- /dev/null +++ b/granite-3.0-8b-base.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b03cb21e46edb50f8c898208316d4d39f7aaf5523b6b576facfc84abbe2c50c2 +size 8684229888 diff --git a/granite-3.0-8b-base.f16.gguf b/granite-3.0-8b-base.f16.gguf new file mode 100644 index 0000000..7625203 --- /dev/null +++ b/granite-3.0-8b-base.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fbe8244c06688fd2e049066834c73eb459d1e0fe05d42d0b3fb7014eb13de33f +size 16344077568