From d988720c766be6bc1e09590e88f73e08103a6518 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Wed, 6 May 2026 04:20:37 +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/gpt-oss-4B-i1-GGUF Source: Original Platform --- .gitattributes | 60 +++++++++++++++++++++++++++ README.md | 85 ++++++++++++++++++++++++++++++++++++++ gpt-oss-4B.i1-IQ1_M.gguf | 3 ++ gpt-oss-4B.i1-IQ1_S.gguf | 3 ++ gpt-oss-4B.i1-IQ2_M.gguf | 3 ++ gpt-oss-4B.i1-IQ2_S.gguf | 3 ++ gpt-oss-4B.i1-IQ2_XS.gguf | 3 ++ gpt-oss-4B.i1-IQ2_XXS.gguf | 3 ++ gpt-oss-4B.i1-IQ3_M.gguf | 3 ++ gpt-oss-4B.i1-IQ3_S.gguf | 3 ++ gpt-oss-4B.i1-IQ3_XS.gguf | 3 ++ gpt-oss-4B.i1-IQ3_XXS.gguf | 3 ++ gpt-oss-4B.i1-IQ4_NL.gguf | 3 ++ gpt-oss-4B.i1-IQ4_XS.gguf | 3 ++ gpt-oss-4B.i1-Q2_K.gguf | 3 ++ gpt-oss-4B.i1-Q2_K_S.gguf | 3 ++ gpt-oss-4B.i1-Q3_K_L.gguf | 3 ++ gpt-oss-4B.i1-Q3_K_M.gguf | 3 ++ gpt-oss-4B.i1-Q3_K_S.gguf | 3 ++ gpt-oss-4B.i1-Q4_0.gguf | 3 ++ gpt-oss-4B.i1-Q4_1.gguf | 3 ++ gpt-oss-4B.i1-Q4_K_M.gguf | 3 ++ gpt-oss-4B.i1-Q4_K_S.gguf | 3 ++ gpt-oss-4B.i1-Q5_K_M.gguf | 3 ++ gpt-oss-4B.i1-Q5_K_S.gguf | 3 ++ gpt-oss-4B.i1-Q6_K.gguf | 3 ++ gpt-oss-4B.imatrix.gguf | 3 ++ 27 files changed, 220 insertions(+) create mode 100644 .gitattributes create mode 100644 README.md create mode 100644 gpt-oss-4B.i1-IQ1_M.gguf create mode 100644 gpt-oss-4B.i1-IQ1_S.gguf create mode 100644 gpt-oss-4B.i1-IQ2_M.gguf create mode 100644 gpt-oss-4B.i1-IQ2_S.gguf create mode 100644 gpt-oss-4B.i1-IQ2_XS.gguf create mode 100644 gpt-oss-4B.i1-IQ2_XXS.gguf create mode 100644 gpt-oss-4B.i1-IQ3_M.gguf create mode 100644 gpt-oss-4B.i1-IQ3_S.gguf create mode 100644 gpt-oss-4B.i1-IQ3_XS.gguf create mode 100644 gpt-oss-4B.i1-IQ3_XXS.gguf create mode 100644 gpt-oss-4B.i1-IQ4_NL.gguf create mode 100644 gpt-oss-4B.i1-IQ4_XS.gguf create mode 100644 gpt-oss-4B.i1-Q2_K.gguf create mode 100644 gpt-oss-4B.i1-Q2_K_S.gguf create mode 100644 gpt-oss-4B.i1-Q3_K_L.gguf create mode 100644 gpt-oss-4B.i1-Q3_K_M.gguf create mode 100644 gpt-oss-4B.i1-Q3_K_S.gguf create mode 100644 gpt-oss-4B.i1-Q4_0.gguf create mode 100644 gpt-oss-4B.i1-Q4_1.gguf create mode 100644 gpt-oss-4B.i1-Q4_K_M.gguf create mode 100644 gpt-oss-4B.i1-Q4_K_S.gguf create mode 100644 gpt-oss-4B.i1-Q5_K_M.gguf create mode 100644 gpt-oss-4B.i1-Q5_K_S.gguf create mode 100644 gpt-oss-4B.i1-Q6_K.gguf create mode 100644 gpt-oss-4B.imatrix.gguf diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..6ee4a3f --- /dev/null +++ b/.gitattributes @@ -0,0 +1,60 @@ +*.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 +gpt-oss-4B.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +gpt-oss-4B.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +gpt-oss-4B.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +gpt-oss-4B.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +gpt-oss-4B.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +gpt-oss-4B.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +gpt-oss-4B.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +gpt-oss-4B.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +gpt-oss-4B.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +gpt-oss-4B.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +gpt-oss-4B.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +gpt-oss-4B.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +gpt-oss-4B.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +gpt-oss-4B.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +gpt-oss-4B.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gpt-oss-4B.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +gpt-oss-4B.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gpt-oss-4B.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gpt-oss-4B.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +gpt-oss-4B.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +gpt-oss-4B.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gpt-oss-4B.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gpt-oss-4B.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gpt-oss-4B.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gpt-oss-4B.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..69a63da --- /dev/null +++ b/README.md @@ -0,0 +1,85 @@ +--- +base_model: TroyDoesAI/gpt-oss-4B +language: +- en +library_name: transformers +license: artistic-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/TroyDoesAI/gpt-oss-4B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#gpt-oss-4B-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/gpt-oss-4B-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/gpt-oss-4B-i1-GGUF/resolve/main/gpt-oss-4B.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/gpt-oss-4B-i1-GGUF/resolve/main/gpt-oss-4B.i1-IQ1_M.gguf) | i1-IQ1_M | 2.7 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/gpt-oss-4B-i1-GGUF/resolve/main/gpt-oss-4B.i1-IQ1_S.gguf) | i1-IQ1_S | 2.7 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/gpt-oss-4B-i1-GGUF/resolve/main/gpt-oss-4B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/gpt-oss-4B-i1-GGUF/resolve/main/gpt-oss-4B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/gpt-oss-4B-i1-GGUF/resolve/main/gpt-oss-4B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 2.7 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/gpt-oss-4B-i1-GGUF/resolve/main/gpt-oss-4B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 2.7 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/gpt-oss-4B-i1-GGUF/resolve/main/gpt-oss-4B.i1-IQ2_M.gguf) | i1-IQ2_M | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/gpt-oss-4B-i1-GGUF/resolve/main/gpt-oss-4B.i1-IQ2_S.gguf) | i1-IQ2_S | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/gpt-oss-4B-i1-GGUF/resolve/main/gpt-oss-4B.i1-IQ3_S.gguf) | i1-IQ3_S | 2.7 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/gpt-oss-4B-i1-GGUF/resolve/main/gpt-oss-4B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/gpt-oss-4B-i1-GGUF/resolve/main/gpt-oss-4B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 2.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/gpt-oss-4B-i1-GGUF/resolve/main/gpt-oss-4B.i1-Q2_K.gguf) | i1-Q2_K | 2.7 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/gpt-oss-4B-i1-GGUF/resolve/main/gpt-oss-4B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/gpt-oss-4B-i1-GGUF/resolve/main/gpt-oss-4B.i1-Q4_0.gguf) | i1-Q4_0 | 2.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/gpt-oss-4B-i1-GGUF/resolve/main/gpt-oss-4B.i1-IQ4_NL.gguf) | i1-IQ4_NL | 2.8 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/gpt-oss-4B-i1-GGUF/resolve/main/gpt-oss-4B.i1-IQ3_M.gguf) | i1-IQ3_M | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/gpt-oss-4B-i1-GGUF/resolve/main/gpt-oss-4B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 2.9 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/gpt-oss-4B-i1-GGUF/resolve/main/gpt-oss-4B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 3.0 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/gpt-oss-4B-i1-GGUF/resolve/main/gpt-oss-4B.i1-Q4_1.gguf) | i1-Q4_1 | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/gpt-oss-4B-i1-GGUF/resolve/main/gpt-oss-4B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 3.2 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/gpt-oss-4B-i1-GGUF/resolve/main/gpt-oss-4B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 3.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/gpt-oss-4B-i1-GGUF/resolve/main/gpt-oss-4B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/gpt-oss-4B-i1-GGUF/resolve/main/gpt-oss-4B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/gpt-oss-4B-i1-GGUF/resolve/main/gpt-oss-4B.i1-Q6_K.gguf) | i1-Q6_K | 4.5 | practically like static Q6_K | + +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/gpt-oss-4B.i1-IQ1_M.gguf b/gpt-oss-4B.i1-IQ1_M.gguf new file mode 100644 index 0000000..d177ad9 --- /dev/null +++ b/gpt-oss-4B.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fafff569d18a9d53ccaaf29062dae3def054878b1bc9ae57b91748523eece928 +size 2580023840 diff --git a/gpt-oss-4B.i1-IQ1_S.gguf b/gpt-oss-4B.i1-IQ1_S.gguf new file mode 100644 index 0000000..1dd8998 --- /dev/null +++ b/gpt-oss-4B.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6d044a01ddb2e9a1a76259c0e8de12389c869662235ced1b89d2db78ba1ed7f +size 2580023840 diff --git a/gpt-oss-4B.i1-IQ2_M.gguf b/gpt-oss-4B.i1-IQ2_M.gguf new file mode 100644 index 0000000..27291df --- /dev/null +++ b/gpt-oss-4B.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02b18ec73f9bc3015b3f7366c65d265177f1762220cb7c4deb35381c38e578a6 +size 2628684320 diff --git a/gpt-oss-4B.i1-IQ2_S.gguf b/gpt-oss-4B.i1-IQ2_S.gguf new file mode 100644 index 0000000..b7a9477 --- /dev/null +++ b/gpt-oss-4B.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae3fbc6f9759c4b2f64016828e9217b4cb88b264f30ccc32b0e13cd829fa8601 +size 2628684320 diff --git a/gpt-oss-4B.i1-IQ2_XS.gguf b/gpt-oss-4B.i1-IQ2_XS.gguf new file mode 100644 index 0000000..ba25b2c --- /dev/null +++ b/gpt-oss-4B.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43056a8fe5210e1e97f60864c951179060e1db7700dc9bfa824f83a0b59c28ae +size 2588871200 diff --git a/gpt-oss-4B.i1-IQ2_XXS.gguf b/gpt-oss-4B.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..edde278 --- /dev/null +++ b/gpt-oss-4B.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca6131f6cf064a822da88c56725ff9cd2adbee8ca541b5fa49db5a51d618d740 +size 2580023840 diff --git a/gpt-oss-4B.i1-IQ3_M.gguf b/gpt-oss-4B.i1-IQ3_M.gguf new file mode 100644 index 0000000..0cc1e78 --- /dev/null +++ b/gpt-oss-4B.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e845b36644016dbc3f1b31bb8dffd4925b11023558c84d8cc9d3c1b246eb127b +size 2678727200 diff --git a/gpt-oss-4B.i1-IQ3_S.gguf b/gpt-oss-4B.i1-IQ3_S.gguf new file mode 100644 index 0000000..bf80a81 --- /dev/null +++ b/gpt-oss-4B.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b67dfa521e1b7cb324e48346d890e56fb87ea33646d165ed657ef6a149af396 +size 2628684320 diff --git a/gpt-oss-4B.i1-IQ3_XS.gguf b/gpt-oss-4B.i1-IQ3_XS.gguf new file mode 100644 index 0000000..5141406 --- /dev/null +++ b/gpt-oss-4B.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dbe76e0658a0a9d68e5949eaf7398f98c5e8fdcc9ee33910f8ec287078c2dc6e +size 2628684320 diff --git a/gpt-oss-4B.i1-IQ3_XXS.gguf b/gpt-oss-4B.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..20a9ce1 --- /dev/null +++ b/gpt-oss-4B.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c50362982765949aa39a78aae32388312d44261f582d2bd8e77a291fa2edb0c5 +size 2628684320 diff --git a/gpt-oss-4B.i1-IQ4_NL.gguf b/gpt-oss-4B.i1-IQ4_NL.gguf new file mode 100644 index 0000000..d4ae5c6 --- /dev/null +++ b/gpt-oss-4B.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:079c009202c274bc857f973cf8830714191370d601a5335b041e81e64467cb66 +size 2668497440 diff --git a/gpt-oss-4B.i1-IQ4_XS.gguf b/gpt-oss-4B.i1-IQ4_XS.gguf new file mode 100644 index 0000000..d0c2eea --- /dev/null +++ b/gpt-oss-4B.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c720d3f1611fc71b05bc9a4c644ff81d024d6c8d4ec28d32c7eff6cbb04cf24d +size 2659650080 diff --git a/gpt-oss-4B.i1-Q2_K.gguf b/gpt-oss-4B.i1-Q2_K.gguf new file mode 100644 index 0000000..2ba62da --- /dev/null +++ b/gpt-oss-4B.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b29630e42758e9930869b36d54e3208a56208d36518e37bc61e430f5d808b612 +size 2628684320 diff --git a/gpt-oss-4B.i1-Q2_K_S.gguf b/gpt-oss-4B.i1-Q2_K_S.gguf new file mode 100644 index 0000000..db7d1ae --- /dev/null +++ b/gpt-oss-4B.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5374330a96478446d8c47465d8c2e5ce9a8eb40a1aabf6a0bad2544e750726c +size 2612372000 diff --git a/gpt-oss-4B.i1-Q3_K_L.gguf b/gpt-oss-4B.i1-Q3_K_L.gguf new file mode 100644 index 0000000..390cf0c --- /dev/null +++ b/gpt-oss-4B.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99537624b67d6f3d290be5af878e7743f03c49e58810d224e64f36d66e20e6a8 +size 2853186080 diff --git a/gpt-oss-4B.i1-Q3_K_M.gguf b/gpt-oss-4B.i1-Q3_K_M.gguf new file mode 100644 index 0000000..d05df3e --- /dev/null +++ b/gpt-oss-4B.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8a11f717cae29915829dfedfbddfab965bba3b1236d04eb3abddad935e829da +size 2768076320 diff --git a/gpt-oss-4B.i1-Q3_K_S.gguf b/gpt-oss-4B.i1-Q3_K_S.gguf new file mode 100644 index 0000000..5eb6cbc --- /dev/null +++ b/gpt-oss-4B.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8cf5bff5626e46087d77e998bd467d0bbfba6b7313340f79de8a048bc504f174 +size 2624260640 diff --git a/gpt-oss-4B.i1-Q4_0.gguf b/gpt-oss-4B.i1-Q4_0.gguf new file mode 100644 index 0000000..fb22068 --- /dev/null +++ b/gpt-oss-4B.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:669254f720dde4efd8e9a0f022b257b56bc9732016e14dcbc279dbfe54de2b01 +size 2668082720 diff --git a/gpt-oss-4B.i1-Q4_1.gguf b/gpt-oss-4B.i1-Q4_1.gguf new file mode 100644 index 0000000..cadc461 --- /dev/null +++ b/gpt-oss-4B.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d52893c4975ff5291849fb619364c809ee1587895fd69b6582b6257d5f431635 +size 2887170080 diff --git a/gpt-oss-4B.i1-Q4_K_M.gguf b/gpt-oss-4B.i1-Q4_K_M.gguf new file mode 100644 index 0000000..7056e60 --- /dev/null +++ b/gpt-oss-4B.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:492309c93218243254c641eb6617cada1233065efd5b67dca13efd92e39f8ca4 +size 3233023520 diff --git a/gpt-oss-4B.i1-Q4_K_S.gguf b/gpt-oss-4B.i1-Q4_K_S.gguf new file mode 100644 index 0000000..91af191 --- /dev/null +++ b/gpt-oss-4B.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e887768ba762b36661d7a9728b3d57e81a14201dcbb49c69059125418a465e97 +size 3083678240 diff --git a/gpt-oss-4B.i1-Q5_K_M.gguf b/gpt-oss-4B.i1-Q5_K_M.gguf new file mode 100644 index 0000000..831293f --- /dev/null +++ b/gpt-oss-4B.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea3deba58de76aa02bda0499bf9d7425b57f3d930b5e627515a0d2e2d7d33e57 +size 3450037280 diff --git a/gpt-oss-4B.i1-Q5_K_S.gguf b/gpt-oss-4B.i1-Q5_K_S.gguf new file mode 100644 index 0000000..b6bfed2 --- /dev/null +++ b/gpt-oss-4B.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c97ff43b2b572e808dd5568b4baea59195635e7b0551fdba98f348174deb1bf +size 3320091680 diff --git a/gpt-oss-4B.i1-Q6_K.gguf b/gpt-oss-4B.i1-Q6_K.gguf new file mode 100644 index 0000000..44982c5 --- /dev/null +++ b/gpt-oss-4B.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad607f85946fbae17908f128371a2b28cabd27f9567a3f0c2ac1b5169e9864fb +size 4395760160 diff --git a/gpt-oss-4B.imatrix.gguf b/gpt-oss-4B.imatrix.gguf new file mode 100644 index 0000000..7c19099 --- /dev/null +++ b/gpt-oss-4B.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13c3f5e628a8a98e663e6d988ab651b8bc2182c2b6e667978eecb4b99a382caf +size 4848544