commit 8ee45454dd281b0c27d3f551565e875083f2f763 Author: ModelHub XC Date: Thu Aug 13 17:07:16 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/granite-speech-4.1-2b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ae2058f --- /dev/null +++ b/.gitattributes @@ -0,0 +1,49 @@ +*.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-speech-4.1-2b.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +granite-speech-4.1-2b.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text +granite-speech-4.1-2b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +granite-speech-4.1-2b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +granite-speech-4.1-2b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +granite-speech-4.1-2b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +granite-speech-4.1-2b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +granite-speech-4.1-2b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +granite-speech-4.1-2b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +granite-speech-4.1-2b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +granite-speech-4.1-2b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +granite-speech-4.1-2b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +granite-speech-4.1-2b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +granite-speech-4.1-2b.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..196f306 --- /dev/null +++ b/README.md @@ -0,0 +1,80 @@ +--- +base_model: ibm-granite/granite-speech-4.1-2b +language: +- multilingual +- en +- fr +- de +- es +- pt +- ja +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/ibm-granite/granite-speech-4.1-2b + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#granite-speech-4.1-2b-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/granite-speech-4.1-2b-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-speech-4.1-2b-GGUF/resolve/main/granite-speech-4.1-2b.Q2_K.gguf) | Q2_K | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/granite-speech-4.1-2b-GGUF/resolve/main/granite-speech-4.1-2b.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.9 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/granite-speech-4.1-2b-GGUF/resolve/main/granite-speech-4.1-2b.Q3_K_S.gguf) | Q3_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/granite-speech-4.1-2b-GGUF/resolve/main/granite-speech-4.1-2b.Q3_K_M.gguf) | Q3_K_M | 1.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/granite-speech-4.1-2b-GGUF/resolve/main/granite-speech-4.1-2b.Q3_K_L.gguf) | Q3_K_L | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/granite-speech-4.1-2b-GGUF/resolve/main/granite-speech-4.1-2b.IQ4_XS.gguf) | IQ4_XS | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/granite-speech-4.1-2b-GGUF/resolve/main/granite-speech-4.1-2b.Q4_K_S.gguf) | Q4_K_S | 1.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/granite-speech-4.1-2b-GGUF/resolve/main/granite-speech-4.1-2b.Q4_K_M.gguf) | Q4_K_M | 1.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/granite-speech-4.1-2b-GGUF/resolve/main/granite-speech-4.1-2b.mmproj-f16.gguf) | mmproj-f16 | 1.3 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/granite-speech-4.1-2b-GGUF/resolve/main/granite-speech-4.1-2b.Q5_K_S.gguf) | Q5_K_S | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/granite-speech-4.1-2b-GGUF/resolve/main/granite-speech-4.1-2b.Q5_K_M.gguf) | Q5_K_M | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/granite-speech-4.1-2b-GGUF/resolve/main/granite-speech-4.1-2b.Q6_K.gguf) | Q6_K | 1.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/granite-speech-4.1-2b-GGUF/resolve/main/granite-speech-4.1-2b.Q8_0.gguf) | Q8_0 | 2.1 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/granite-speech-4.1-2b-GGUF/resolve/main/granite-speech-4.1-2b.f16.gguf) | f16 | 3.8 | 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-speech-4.1-2b.IQ4_XS.gguf b/granite-speech-4.1-2b.IQ4_XS.gguf new file mode 100644 index 0000000..81ff7ea --- /dev/null +++ b/granite-speech-4.1-2b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9736d7e9b756aa4824373620c5f0eb8486a67d8f5aa66749c88fc760b5f5c1e +size 1052707328 diff --git a/granite-speech-4.1-2b.Q2_K.gguf b/granite-speech-4.1-2b.Q2_K.gguf new file mode 100644 index 0000000..e51f844 --- /dev/null +++ b/granite-speech-4.1-2b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e803105bd476c14234be43b94b66e7af7e8c8e31655fdf630a07333388220f0 +size 769132640 diff --git a/granite-speech-4.1-2b.Q3_K_L.gguf b/granite-speech-4.1-2b.Q3_K_L.gguf new file mode 100644 index 0000000..00f2d54 --- /dev/null +++ b/granite-speech-4.1-2b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a58eac03760801bbcd5e7a78d658aeb86354d9c23c91ff4b074ddec6e787d2b8 +size 1014466880 diff --git a/granite-speech-4.1-2b.Q3_K_M.gguf b/granite-speech-4.1-2b.Q3_K_M.gguf new file mode 100644 index 0000000..1728701 --- /dev/null +++ b/granite-speech-4.1-2b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22e4ca5a9f7bd89bde3a7eb4d6e47146c847ebfb80531c01edb0b9db66d1cce6 +size 948668736 diff --git a/granite-speech-4.1-2b.Q3_K_S.gguf b/granite-speech-4.1-2b.Q3_K_S.gguf new file mode 100644 index 0000000..d206f7f --- /dev/null +++ b/granite-speech-4.1-2b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8654cf9756fcd7b975e3d2a12a4ca8bbff072ba0969badb83776f3e92f56ed87 +size 873892160 diff --git a/granite-speech-4.1-2b.Q4_K_M.gguf b/granite-speech-4.1-2b.Q4_K_M.gguf new file mode 100644 index 0000000..55b245e --- /dev/null +++ b/granite-speech-4.1-2b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91dc3a58c6bebbdfc839645367d70f53a6f8621b1ca38f3c08c00033949f6071 +size 1139247680 diff --git a/granite-speech-4.1-2b.Q4_K_S.gguf b/granite-speech-4.1-2b.Q4_K_S.gguf new file mode 100644 index 0000000..c027843 --- /dev/null +++ b/granite-speech-4.1-2b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a33ab069393d874efb81cd88403a0c75939a2cd77e48b7ccac0cdf9f77299477 +size 1096354368 diff --git a/granite-speech-4.1-2b.Q5_K_M.gguf b/granite-speech-4.1-2b.Q5_K_M.gguf new file mode 100644 index 0000000..46ca477 --- /dev/null +++ b/granite-speech-4.1-2b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0c62cbaaae4fbca500855a83431cfdcb1bae0bdd37c7cc8796f6678becdac6a +size 1319603008 diff --git a/granite-speech-4.1-2b.Q5_K_S.gguf b/granite-speech-4.1-2b.Q5_K_S.gguf new file mode 100644 index 0000000..3663fda --- /dev/null +++ b/granite-speech-4.1-2b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ddc116b91075f252e47e933b2955dc76f2404b3b137eb3eff438f894bd8da64 +size 1294535488 diff --git a/granite-speech-4.1-2b.Q6_K.gguf b/granite-speech-4.1-2b.Q6_K.gguf new file mode 100644 index 0000000..9194e6c --- /dev/null +++ b/granite-speech-4.1-2b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1adb2b44c860ac4bd5065c662ada4941f1fcf48ba6cc7ef0606d20b7e24777aa +size 1511230560 diff --git a/granite-speech-4.1-2b.Q8_0.gguf b/granite-speech-4.1-2b.Q8_0.gguf new file mode 100644 index 0000000..ea0d0ae --- /dev/null +++ b/granite-speech-4.1-2b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4949fff757ba8fd7c1176e5fe40fab36ae844fc4592acf8b999ec047cf8f3dab +size 1956155424 diff --git a/granite-speech-4.1-2b.f16.gguf b/granite-speech-4.1-2b.f16.gguf new file mode 100644 index 0000000..738dc8e --- /dev/null +++ b/granite-speech-4.1-2b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bae1e43eb769560c86a319db3ef69c7e7415e903b1c2c3193f16507820889d8b +size 3678445344 diff --git a/granite-speech-4.1-2b.mmproj-Q8_0.gguf b/granite-speech-4.1-2b.mmproj-Q8_0.gguf new file mode 100644 index 0000000..111df12 --- /dev/null +++ b/granite-speech-4.1-2b.mmproj-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29eec001ed3639edfcf0fc6d30906a0a1106133dac3fd5bee75ffad9147a3377 +size 810870912 diff --git a/granite-speech-4.1-2b.mmproj-f16.gguf b/granite-speech-4.1-2b.mmproj-f16.gguf new file mode 100644 index 0000000..1c764fb --- /dev/null +++ b/granite-speech-4.1-2b.mmproj-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4bbf0d1d6442a7b0f732d30f6898d231f1631bc6c90163761883c5c61aaff256 +size 1159354752