From cecca9940de07a559823ad99b9cd3f4c6c5118fd Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Sat, 8 Aug 2026 23:01:16 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: mradermacher/Granite-4.1-3b-coder-GGUF Source: Original Platform --- .gitattributes | 47 +++++++++++++++++++ Granite-4.1-3b-coder.IQ4_XS.gguf | 3 ++ Granite-4.1-3b-coder.Q2_K.gguf | 3 ++ Granite-4.1-3b-coder.Q3_K_L.gguf | 3 ++ Granite-4.1-3b-coder.Q3_K_M.gguf | 3 ++ Granite-4.1-3b-coder.Q3_K_S.gguf | 3 ++ Granite-4.1-3b-coder.Q4_K_M.gguf | 3 ++ Granite-4.1-3b-coder.Q4_K_S.gguf | 3 ++ Granite-4.1-3b-coder.Q5_K_M.gguf | 3 ++ Granite-4.1-3b-coder.Q5_K_S.gguf | 3 ++ Granite-4.1-3b-coder.Q6_K.gguf | 3 ++ Granite-4.1-3b-coder.Q8_0.gguf | 3 ++ Granite-4.1-3b-coder.f16.gguf | 3 ++ README.md | 77 ++++++++++++++++++++++++++++++++ 14 files changed, 160 insertions(+) create mode 100644 .gitattributes create mode 100644 Granite-4.1-3b-coder.IQ4_XS.gguf create mode 100644 Granite-4.1-3b-coder.Q2_K.gguf create mode 100644 Granite-4.1-3b-coder.Q3_K_L.gguf create mode 100644 Granite-4.1-3b-coder.Q3_K_M.gguf create mode 100644 Granite-4.1-3b-coder.Q3_K_S.gguf create mode 100644 Granite-4.1-3b-coder.Q4_K_M.gguf create mode 100644 Granite-4.1-3b-coder.Q4_K_S.gguf create mode 100644 Granite-4.1-3b-coder.Q5_K_M.gguf create mode 100644 Granite-4.1-3b-coder.Q5_K_S.gguf create mode 100644 Granite-4.1-3b-coder.Q6_K.gguf create mode 100644 Granite-4.1-3b-coder.Q8_0.gguf create mode 100644 Granite-4.1-3b-coder.f16.gguf create mode 100644 README.md diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..4698440 --- /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-4.1-3b-coder.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Granite-4.1-3b-coder.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Granite-4.1-3b-coder.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Granite-4.1-3b-coder.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Granite-4.1-3b-coder.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Granite-4.1-3b-coder.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Granite-4.1-3b-coder.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Granite-4.1-3b-coder.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Granite-4.1-3b-coder.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Granite-4.1-3b-coder.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Granite-4.1-3b-coder.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Granite-4.1-3b-coder.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Granite-4.1-3b-coder.IQ4_XS.gguf b/Granite-4.1-3b-coder.IQ4_XS.gguf new file mode 100644 index 0000000..65e6e7f --- /dev/null +++ b/Granite-4.1-3b-coder.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:720b34c5a4760ee10a1bb3068be9e45fc11fb77ca587b590c8865e1c9612c122 +size 1910881824 diff --git a/Granite-4.1-3b-coder.Q2_K.gguf b/Granite-4.1-3b-coder.Q2_K.gguf new file mode 100644 index 0000000..11404ff --- /dev/null +++ b/Granite-4.1-3b-coder.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1dfb78b9ee9248a8d4c99bd94443913c42dccc5cb7c5cc0a2ba1c1419dc0bbdf +size 1371438624 diff --git a/Granite-4.1-3b-coder.Q3_K_L.gguf b/Granite-4.1-3b-coder.Q3_K_L.gguf new file mode 100644 index 0000000..5fa6152 --- /dev/null +++ b/Granite-4.1-3b-coder.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd4477e53e45d31b942aeb7008c1c3b154a37cdc5a91f8e4b493876fc2c50620 +size 1864187424 diff --git a/Granite-4.1-3b-coder.Q3_K_M.gguf b/Granite-4.1-3b-coder.Q3_K_M.gguf new file mode 100644 index 0000000..87420b4 --- /dev/null +++ b/Granite-4.1-3b-coder.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa00a33a69b4006d9edb9e538cbfb50d1279700564f696f7e165aa2c06b168d9 +size 1725578784 diff --git a/Granite-4.1-3b-coder.Q3_K_S.gguf b/Granite-4.1-3b-coder.Q3_K_S.gguf new file mode 100644 index 0000000..cdf0045 --- /dev/null +++ b/Granite-4.1-3b-coder.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:135ad4f907b33b10b35be14a70c9dc2c28b6ecf043bb55ff49f435ad9f5e4f57 +size 1566817824 diff --git a/Granite-4.1-3b-coder.Q4_K_M.gguf b/Granite-4.1-3b-coder.Q4_K_M.gguf new file mode 100644 index 0000000..40cdf69 --- /dev/null +++ b/Granite-4.1-3b-coder.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b46268eadf3c8c581b50df5f82debe2d2a7a33b747f70764cfa1b0614cf4c5c9 +size 2099502624 diff --git a/Granite-4.1-3b-coder.Q4_K_S.gguf b/Granite-4.1-3b-coder.Q4_K_S.gguf new file mode 100644 index 0000000..69c748c --- /dev/null +++ b/Granite-4.1-3b-coder.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3991ebade649f27c30e7ca9f9bb8cf31fe32b41be17229c21e39ecbf7496519d +size 1998372384 diff --git a/Granite-4.1-3b-coder.Q5_K_M.gguf b/Granite-4.1-3b-coder.Q5_K_M.gguf new file mode 100644 index 0000000..35cda7f --- /dev/null +++ b/Granite-4.1-3b-coder.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d87545270111f04c33c23367403d1efed958ac0814d28a4df54554b3f3426257 +size 2437013024 diff --git a/Granite-4.1-3b-coder.Q5_K_S.gguf b/Granite-4.1-3b-coder.Q5_K_S.gguf new file mode 100644 index 0000000..6f7dbcd --- /dev/null +++ b/Granite-4.1-3b-coder.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ecf288cbc9ae6c3f9a5e79fb0d6ffefbac9db7ebc3dab86a3a7f0703dcac1755 +size 2377825824 diff --git a/Granite-4.1-3b-coder.Q6_K.gguf b/Granite-4.1-3b-coder.Q6_K.gguf new file mode 100644 index 0000000..34a663b --- /dev/null +++ b/Granite-4.1-3b-coder.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4cc3c814e6f74870bfe0a75da62c1245e81e480f165bb99932b270f2c2705b6a +size 2795617824 diff --git a/Granite-4.1-3b-coder.Q8_0.gguf b/Granite-4.1-3b-coder.Q8_0.gguf new file mode 100644 index 0000000..09ecec0 --- /dev/null +++ b/Granite-4.1-3b-coder.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f04ff031b1db5f552a3b596f66fa448344e72de3d6c0132d8ffd60e2720e0d0 +size 3619692064 diff --git a/Granite-4.1-3b-coder.f16.gguf b/Granite-4.1-3b-coder.f16.gguf new file mode 100644 index 0000000..847d2e9 --- /dev/null +++ b/Granite-4.1-3b-coder.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:133325bcb08fb9636def93b6da6c9da8f704871510ceebd24ff3b600478f227b +size 6809656864 diff --git a/README.md b/README.md new file mode 100644 index 0000000..5ab216d --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: ertghiu256/Granite-4.1-3b-coder +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- granite +--- +## About + + + + + + + + + +static quants of https://huggingface.co/ertghiu256/Granite-4.1-3b-coder + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Granite-4.1-3b-coder-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/Granite-4.1-3b-coder-GGUF/resolve/main/Granite-4.1-3b-coder.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Granite-4.1-3b-coder-GGUF/resolve/main/Granite-4.1-3b-coder.Q3_K_S.gguf) | Q3_K_S | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/Granite-4.1-3b-coder-GGUF/resolve/main/Granite-4.1-3b-coder.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Granite-4.1-3b-coder-GGUF/resolve/main/Granite-4.1-3b-coder.Q3_K_L.gguf) | Q3_K_L | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Granite-4.1-3b-coder-GGUF/resolve/main/Granite-4.1-3b-coder.IQ4_XS.gguf) | IQ4_XS | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Granite-4.1-3b-coder-GGUF/resolve/main/Granite-4.1-3b-coder.Q4_K_S.gguf) | Q4_K_S | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Granite-4.1-3b-coder-GGUF/resolve/main/Granite-4.1-3b-coder.Q4_K_M.gguf) | Q4_K_M | 2.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Granite-4.1-3b-coder-GGUF/resolve/main/Granite-4.1-3b-coder.Q5_K_S.gguf) | Q5_K_S | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/Granite-4.1-3b-coder-GGUF/resolve/main/Granite-4.1-3b-coder.Q5_K_M.gguf) | Q5_K_M | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/Granite-4.1-3b-coder-GGUF/resolve/main/Granite-4.1-3b-coder.Q6_K.gguf) | Q6_K | 2.9 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Granite-4.1-3b-coder-GGUF/resolve/main/Granite-4.1-3b-coder.Q8_0.gguf) | Q8_0 | 3.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Granite-4.1-3b-coder-GGUF/resolve/main/Granite-4.1-3b-coder.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. + +