commit 7ecfca9433558caff948afe1c5b811eb5a979911 Author: ModelHub XC Date: Mon Jun 1 08:33:16 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/granite-speech-3.3-2b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..94b3c88 --- /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-3.3-2b.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +granite-speech-3.3-2b.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text +granite-speech-3.3-2b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +granite-speech-3.3-2b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +granite-speech-3.3-2b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +granite-speech-3.3-2b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +granite-speech-3.3-2b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +granite-speech-3.3-2b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +granite-speech-3.3-2b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +granite-speech-3.3-2b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +granite-speech-3.3-2b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +granite-speech-3.3-2b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +granite-speech-3.3-2b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +granite-speech-3.3-2b.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..14b1e54 --- /dev/null +++ b/README.md @@ -0,0 +1,79 @@ +--- +base_model: ibm-granite/granite-speech-3.3-2b +language: +- multilingual +- en +- fr +- de +- es +- pt +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-3.3-2b + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#granite-speech-3.3-2b-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/granite-speech-3.3-2b-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-3.3-2b-GGUF/resolve/main/granite-speech-3.3-2b.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.9 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/granite-speech-3.3-2b-GGUF/resolve/main/granite-speech-3.3-2b.Q2_K.gguf) | Q2_K | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/granite-speech-3.3-2b-GGUF/resolve/main/granite-speech-3.3-2b.Q3_K_S.gguf) | Q3_K_S | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/granite-speech-3.3-2b-GGUF/resolve/main/granite-speech-3.3-2b.mmproj-f16.gguf) | mmproj-f16 | 1.3 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/granite-speech-3.3-2b-GGUF/resolve/main/granite-speech-3.3-2b.Q3_K_M.gguf) | Q3_K_M | 1.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/granite-speech-3.3-2b-GGUF/resolve/main/granite-speech-3.3-2b.Q3_K_L.gguf) | Q3_K_L | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/granite-speech-3.3-2b-GGUF/resolve/main/granite-speech-3.3-2b.IQ4_XS.gguf) | IQ4_XS | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/granite-speech-3.3-2b-GGUF/resolve/main/granite-speech-3.3-2b.Q4_K_S.gguf) | Q4_K_S | 1.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/granite-speech-3.3-2b-GGUF/resolve/main/granite-speech-3.3-2b.Q4_K_M.gguf) | Q4_K_M | 1.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/granite-speech-3.3-2b-GGUF/resolve/main/granite-speech-3.3-2b.Q5_K_S.gguf) | Q5_K_S | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/granite-speech-3.3-2b-GGUF/resolve/main/granite-speech-3.3-2b.Q5_K_M.gguf) | Q5_K_M | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/granite-speech-3.3-2b-GGUF/resolve/main/granite-speech-3.3-2b.Q6_K.gguf) | Q6_K | 2.2 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/granite-speech-3.3-2b-GGUF/resolve/main/granite-speech-3.3-2b.Q8_0.gguf) | Q8_0 | 2.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/granite-speech-3.3-2b-GGUF/resolve/main/granite-speech-3.3-2b.f16.gguf) | f16 | 5.2 | 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-3.3-2b.IQ4_XS.gguf b/granite-speech-3.3-2b.IQ4_XS.gguf new file mode 100644 index 0000000..5cd1557 --- /dev/null +++ b/granite-speech-3.3-2b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d9e37717ab59786ba232492a8dd4d629a737ec86a96187129c7bffde93274f1 +size 1397030240 diff --git a/granite-speech-3.3-2b.Q2_K.gguf b/granite-speech-3.3-2b.Q2_K.gguf new file mode 100644 index 0000000..64b976e --- /dev/null +++ b/granite-speech-3.3-2b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:235730493597119f439cbed8a007b92f51752d6d00e8b9829e8ec4bc4019d4cb +size 978255200 diff --git a/granite-speech-3.3-2b.Q3_K_L.gguf b/granite-speech-3.3-2b.Q3_K_L.gguf new file mode 100644 index 0000000..279d6a9 --- /dev/null +++ b/granite-speech-3.3-2b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25e6d81f251c5d9ab4ab87779e5bdc894edfbe0a89a2a00e8f31257dfab90f62 +size 1357380960 diff --git a/granite-speech-3.3-2b.Q3_K_M.gguf b/granite-speech-3.3-2b.Q3_K_M.gguf new file mode 100644 index 0000000..930572d --- /dev/null +++ b/granite-speech-3.3-2b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97bcde66d4ac04439f92ca081c5dca5b5a95929e63eb7c673f47fc1064b3d4aa +size 1251736928 diff --git a/granite-speech-3.3-2b.Q3_K_S.gguf b/granite-speech-3.3-2b.Q3_K_S.gguf new file mode 100644 index 0000000..8202d2b --- /dev/null +++ b/granite-speech-3.3-2b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37567e30577fc65d40094d860f8a1588f8597984012e692db67468ef79cb4066 +size 1130298720 diff --git a/granite-speech-3.3-2b.Q4_K_M.gguf b/granite-speech-3.3-2b.Q4_K_M.gguf new file mode 100644 index 0000000..a8bd3aa --- /dev/null +++ b/granite-speech-3.3-2b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55c87a7b89bd808b08dfd1e7f7f6a2fd3c00c888c00c59ae78b1d3d2619568f5 +size 1545305440 diff --git a/granite-speech-3.3-2b.Q4_K_S.gguf b/granite-speech-3.3-2b.Q4_K_S.gguf new file mode 100644 index 0000000..258f7de --- /dev/null +++ b/granite-speech-3.3-2b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a86e1006d8b8a172f2ce73383c70463ee6db50f6ddfda285383758d851ba982 +size 1464401248 diff --git a/granite-speech-3.3-2b.Q5_K_M.gguf b/granite-speech-3.3-2b.Q5_K_M.gguf new file mode 100644 index 0000000..c5fc104 --- /dev/null +++ b/granite-speech-3.3-2b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e193cb9e2cf90c75572bd137ff288e6aa8e95a843aa0b43636cfef574af77fd +size 1804828000 diff --git a/granite-speech-3.3-2b.Q5_K_S.gguf b/granite-speech-3.3-2b.Q5_K_S.gguf new file mode 100644 index 0000000..f3f48c5 --- /dev/null +++ b/granite-speech-3.3-2b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b1ddaacf519d2d07c173914af31433b7af2d486d7afa2b35e74b61a55a2b06c +size 1757478240 diff --git a/granite-speech-3.3-2b.Q6_K.gguf b/granite-speech-3.3-2b.Q6_K.gguf new file mode 100644 index 0000000..136130e --- /dev/null +++ b/granite-speech-3.3-2b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04b054604b0bdd759799d5b7805a290a67ff77999d676cefd94ced858d7cde49 +size 2080570720 diff --git a/granite-speech-3.3-2b.Q8_0.gguf b/granite-speech-3.3-2b.Q8_0.gguf new file mode 100644 index 0000000..47c8f79 --- /dev/null +++ b/granite-speech-3.3-2b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76a8408181c6ca303e55edd58ef467d89bb40f153859835e775a01bc432e87ea +size 2694122720 diff --git a/granite-speech-3.3-2b.f16.gguf b/granite-speech-3.3-2b.f16.gguf new file mode 100644 index 0000000..0b7fd8d --- /dev/null +++ b/granite-speech-3.3-2b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5db145f43d1aee93a5a0d048673e6289b4b2a2ee221fa201bb6d84876aaa2269 +size 5069162720 diff --git a/granite-speech-3.3-2b.mmproj-Q8_0.gguf b/granite-speech-3.3-2b.mmproj-Q8_0.gguf new file mode 100644 index 0000000..7f6ddb9 --- /dev/null +++ b/granite-speech-3.3-2b.mmproj-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c727372e0650901dac2812b54cbf25751a234d40ebcf560cdb055b94b295a045 +size 810336256 diff --git a/granite-speech-3.3-2b.mmproj-f16.gguf b/granite-speech-3.3-2b.mmproj-f16.gguf new file mode 100644 index 0000000..5f4cd51 --- /dev/null +++ b/granite-speech-3.3-2b.mmproj-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:142ea0e904c011c7d1da6e9c53051c35d38f8b1290938f6593c2928228286114 +size 1158977536