From 01a49b8c41975b9269245c0a57131fb3e91e5f94 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Mon, 6 Jul 2026 20:33:16 +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/gpt-oss-nemo-20b-i1-GGUF Source: Original Platform --- .gitattributes | 59 ++++++++++++++++++ README.md | 103 +++++++++++++++++++++++++++++++ gpt-oss-nemo-20b.i1-IQ1_M.gguf | 3 + gpt-oss-nemo-20b.i1-IQ1_S.gguf | 3 + gpt-oss-nemo-20b.i1-IQ2_M.gguf | 3 + gpt-oss-nemo-20b.i1-IQ2_S.gguf | 3 + gpt-oss-nemo-20b.i1-IQ2_XS.gguf | 3 + gpt-oss-nemo-20b.i1-IQ2_XXS.gguf | 3 + gpt-oss-nemo-20b.i1-IQ3_M.gguf | 3 + gpt-oss-nemo-20b.i1-IQ3_S.gguf | 3 + gpt-oss-nemo-20b.i1-IQ3_XS.gguf | 3 + gpt-oss-nemo-20b.i1-IQ3_XXS.gguf | 3 + gpt-oss-nemo-20b.i1-IQ4_XS.gguf | 3 + gpt-oss-nemo-20b.i1-Q2_K.gguf | 3 + gpt-oss-nemo-20b.i1-Q2_K_S.gguf | 3 + gpt-oss-nemo-20b.i1-Q3_K_L.gguf | 3 + gpt-oss-nemo-20b.i1-Q3_K_M.gguf | 3 + gpt-oss-nemo-20b.i1-Q3_K_S.gguf | 3 + gpt-oss-nemo-20b.i1-Q4_0.gguf | 3 + gpt-oss-nemo-20b.i1-Q4_1.gguf | 3 + gpt-oss-nemo-20b.i1-Q4_K_M.gguf | 3 + gpt-oss-nemo-20b.i1-Q4_K_S.gguf | 3 + gpt-oss-nemo-20b.i1-Q5_K_M.gguf | 3 + gpt-oss-nemo-20b.i1-Q5_K_S.gguf | 3 + gpt-oss-nemo-20b.i1-Q6_K.gguf | 3 + gpt-oss-nemo-20b.imatrix.gguf | 3 + 26 files changed, 234 insertions(+) create mode 100644 .gitattributes create mode 100644 README.md create mode 100644 gpt-oss-nemo-20b.i1-IQ1_M.gguf create mode 100644 gpt-oss-nemo-20b.i1-IQ1_S.gguf create mode 100644 gpt-oss-nemo-20b.i1-IQ2_M.gguf create mode 100644 gpt-oss-nemo-20b.i1-IQ2_S.gguf create mode 100644 gpt-oss-nemo-20b.i1-IQ2_XS.gguf create mode 100644 gpt-oss-nemo-20b.i1-IQ2_XXS.gguf create mode 100644 gpt-oss-nemo-20b.i1-IQ3_M.gguf create mode 100644 gpt-oss-nemo-20b.i1-IQ3_S.gguf create mode 100644 gpt-oss-nemo-20b.i1-IQ3_XS.gguf create mode 100644 gpt-oss-nemo-20b.i1-IQ3_XXS.gguf create mode 100644 gpt-oss-nemo-20b.i1-IQ4_XS.gguf create mode 100644 gpt-oss-nemo-20b.i1-Q2_K.gguf create mode 100644 gpt-oss-nemo-20b.i1-Q2_K_S.gguf create mode 100644 gpt-oss-nemo-20b.i1-Q3_K_L.gguf create mode 100644 gpt-oss-nemo-20b.i1-Q3_K_M.gguf create mode 100644 gpt-oss-nemo-20b.i1-Q3_K_S.gguf create mode 100644 gpt-oss-nemo-20b.i1-Q4_0.gguf create mode 100644 gpt-oss-nemo-20b.i1-Q4_1.gguf create mode 100644 gpt-oss-nemo-20b.i1-Q4_K_M.gguf create mode 100644 gpt-oss-nemo-20b.i1-Q4_K_S.gguf create mode 100644 gpt-oss-nemo-20b.i1-Q5_K_M.gguf create mode 100644 gpt-oss-nemo-20b.i1-Q5_K_S.gguf create mode 100644 gpt-oss-nemo-20b.i1-Q6_K.gguf create mode 100644 gpt-oss-nemo-20b.imatrix.gguf diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d3395f4 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,59 @@ +*.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-nemo-20b.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +gpt-oss-nemo-20b.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +gpt-oss-nemo-20b.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +gpt-oss-nemo-20b.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gpt-oss-nemo-20b.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +gpt-oss-nemo-20b.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gpt-oss-nemo-20b.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gpt-oss-nemo-20b.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +gpt-oss-nemo-20b.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +gpt-oss-nemo-20b.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +gpt-oss-nemo-20b.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gpt-oss-nemo-20b.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +gpt-oss-nemo-20b.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gpt-oss-nemo-20b.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +gpt-oss-nemo-20b.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +gpt-oss-nemo-20b.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +gpt-oss-nemo-20b.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gpt-oss-nemo-20b.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +gpt-oss-nemo-20b.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +gpt-oss-nemo-20b.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gpt-oss-nemo-20b.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +gpt-oss-nemo-20b.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +gpt-oss-nemo-20b.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +gpt-oss-nemo-20b.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..a0bb045 --- /dev/null +++ b/README.md @@ -0,0 +1,103 @@ +--- +base_model: justinj92/gpt-oss-nemo-20b +datasets: +- HuggingFaceH4/Multilingual-Thinking +language: +- multilingual +- en +- es +- ar +- fr +- de +- zh +- ja +- ko +- hi +- ru +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- multilingual +- reasoning +- thinking +- fine-tuned +- lora +- conversational +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/justinj92/gpt-oss-nemo-20b + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#gpt-oss-nemo-20b-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/gpt-oss-nemo-20b-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-nemo-20b-i1-GGUF/resolve/main/gpt-oss-nemo-20b.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/gpt-oss-nemo-20b-i1-GGUF/resolve/main/gpt-oss-nemo-20b.i1-IQ1_M.gguf) | i1-IQ1_M | 12.1 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/gpt-oss-nemo-20b-i1-GGUF/resolve/main/gpt-oss-nemo-20b.i1-IQ1_S.gguf) | i1-IQ1_S | 12.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/gpt-oss-nemo-20b-i1-GGUF/resolve/main/gpt-oss-nemo-20b.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 12.1 | | +| [GGUF](https://huggingface.co/mradermacher/gpt-oss-nemo-20b-i1-GGUF/resolve/main/gpt-oss-nemo-20b.i1-IQ2_XS.gguf) | i1-IQ2_XS | 12.1 | | +| [GGUF](https://huggingface.co/mradermacher/gpt-oss-nemo-20b-i1-GGUF/resolve/main/gpt-oss-nemo-20b.i1-Q3_K_S.gguf) | i1-Q3_K_S | 12.2 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/gpt-oss-nemo-20b-i1-GGUF/resolve/main/gpt-oss-nemo-20b.i1-IQ2_M.gguf) | i1-IQ2_M | 12.2 | | +| [GGUF](https://huggingface.co/mradermacher/gpt-oss-nemo-20b-i1-GGUF/resolve/main/gpt-oss-nemo-20b.i1-IQ2_S.gguf) | i1-IQ2_S | 12.2 | | +| [GGUF](https://huggingface.co/mradermacher/gpt-oss-nemo-20b-i1-GGUF/resolve/main/gpt-oss-nemo-20b.i1-IQ3_S.gguf) | i1-IQ3_S | 12.2 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/gpt-oss-nemo-20b-i1-GGUF/resolve/main/gpt-oss-nemo-20b.i1-IQ3_XS.gguf) | i1-IQ3_XS | 12.2 | | +| [GGUF](https://huggingface.co/mradermacher/gpt-oss-nemo-20b-i1-GGUF/resolve/main/gpt-oss-nemo-20b.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 12.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/gpt-oss-nemo-20b-i1-GGUF/resolve/main/gpt-oss-nemo-20b.i1-Q2_K.gguf) | i1-Q2_K | 12.2 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/gpt-oss-nemo-20b-i1-GGUF/resolve/main/gpt-oss-nemo-20b.i1-IQ4_XS.gguf) | i1-IQ4_XS | 12.2 | | +| [GGUF](https://huggingface.co/mradermacher/gpt-oss-nemo-20b-i1-GGUF/resolve/main/gpt-oss-nemo-20b.i1-Q2_K_S.gguf) | i1-Q2_K_S | 12.2 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/gpt-oss-nemo-20b-i1-GGUF/resolve/main/gpt-oss-nemo-20b.i1-Q4_0.gguf) | i1-Q4_0 | 12.2 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/gpt-oss-nemo-20b-i1-GGUF/resolve/main/gpt-oss-nemo-20b.i1-IQ3_M.gguf) | i1-IQ3_M | 12.3 | | +| [GGUF](https://huggingface.co/mradermacher/gpt-oss-nemo-20b-i1-GGUF/resolve/main/gpt-oss-nemo-20b.i1-Q3_K_M.gguf) | i1-Q3_K_M | 13.0 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/gpt-oss-nemo-20b-i1-GGUF/resolve/main/gpt-oss-nemo-20b.i1-Q3_K_L.gguf) | i1-Q3_K_L | 13.4 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/gpt-oss-nemo-20b-i1-GGUF/resolve/main/gpt-oss-nemo-20b.i1-Q4_1.gguf) | i1-Q4_1 | 13.5 | | +| [GGUF](https://huggingface.co/mradermacher/gpt-oss-nemo-20b-i1-GGUF/resolve/main/gpt-oss-nemo-20b.i1-Q4_K_S.gguf) | i1-Q4_K_S | 14.8 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/gpt-oss-nemo-20b-i1-GGUF/resolve/main/gpt-oss-nemo-20b.i1-Q4_K_M.gguf) | i1-Q4_K_M | 15.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/gpt-oss-nemo-20b-i1-GGUF/resolve/main/gpt-oss-nemo-20b.i1-Q5_K_S.gguf) | i1-Q5_K_S | 16.0 | | +| [GGUF](https://huggingface.co/mradermacher/gpt-oss-nemo-20b-i1-GGUF/resolve/main/gpt-oss-nemo-20b.i1-Q5_K_M.gguf) | i1-Q5_K_M | 17.0 | | +| [GGUF](https://huggingface.co/mradermacher/gpt-oss-nemo-20b-i1-GGUF/resolve/main/gpt-oss-nemo-20b.i1-Q6_K.gguf) | i1-Q6_K | 22.3 | 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-nemo-20b.i1-IQ1_M.gguf b/gpt-oss-nemo-20b.i1-IQ1_M.gguf new file mode 100644 index 0000000..972cd83 --- /dev/null +++ b/gpt-oss-nemo-20b.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:661e45cb34808d2ce39f0dffe8ba93dfa9229d718db82f7a7ca82b97234c09bc +size 12016854272 diff --git a/gpt-oss-nemo-20b.i1-IQ1_S.gguf b/gpt-oss-nemo-20b.i1-IQ1_S.gguf new file mode 100644 index 0000000..7e117ce --- /dev/null +++ b/gpt-oss-nemo-20b.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08fdb44834626339f139703a02dd747cd8d7a7a447e0d755460c6c6dea72cf7c +size 12016854272 diff --git a/gpt-oss-nemo-20b.i1-IQ2_M.gguf b/gpt-oss-nemo-20b.i1-IQ2_M.gguf new file mode 100644 index 0000000..3030008 --- /dev/null +++ b/gpt-oss-nemo-20b.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e81fcd2652ebecb7bcaefcb4c7e63ed6c6c91035f19254f0f4ae11c2925be21d +size 12065514752 diff --git a/gpt-oss-nemo-20b.i1-IQ2_S.gguf b/gpt-oss-nemo-20b.i1-IQ2_S.gguf new file mode 100644 index 0000000..8405beb --- /dev/null +++ b/gpt-oss-nemo-20b.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ec58cb268f3f99d65c43451d8c672e3d3f909674f19c877ed822b7a70d969ea +size 12065514752 diff --git a/gpt-oss-nemo-20b.i1-IQ2_XS.gguf b/gpt-oss-nemo-20b.i1-IQ2_XS.gguf new file mode 100644 index 0000000..4c1691d --- /dev/null +++ b/gpt-oss-nemo-20b.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58897b8d68883a41b217f5bc451fbd9bb1391168b4e72e0f592c313f79f4d7ff +size 12025701632 diff --git a/gpt-oss-nemo-20b.i1-IQ2_XXS.gguf b/gpt-oss-nemo-20b.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..8f05206 --- /dev/null +++ b/gpt-oss-nemo-20b.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b3d15d54fc8f83a7bf79355e11ce1bdca952ca52d76316bbcb668e3d6963a88 +size 12016854272 diff --git a/gpt-oss-nemo-20b.i1-IQ3_M.gguf b/gpt-oss-nemo-20b.i1-IQ3_M.gguf new file mode 100644 index 0000000..28010e6 --- /dev/null +++ b/gpt-oss-nemo-20b.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5a4128a2295d164f6c60a35d8772b0d971ebade6b51a79e7f1ff3c82132acfd +size 12202648832 diff --git a/gpt-oss-nemo-20b.i1-IQ3_S.gguf b/gpt-oss-nemo-20b.i1-IQ3_S.gguf new file mode 100644 index 0000000..dd7b8ce --- /dev/null +++ b/gpt-oss-nemo-20b.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9aaec6c6de311fcef9cfbaf158bb203bc7050e60958e4966e0986ab79ed262a1 +size 12065514752 diff --git a/gpt-oss-nemo-20b.i1-IQ3_XS.gguf b/gpt-oss-nemo-20b.i1-IQ3_XS.gguf new file mode 100644 index 0000000..03a4612 --- /dev/null +++ b/gpt-oss-nemo-20b.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d5bfffa2e89e731ef6f5a0a75982ae1387ca8f497fac8a0c55ae44798d52f64 +size 12065514752 diff --git a/gpt-oss-nemo-20b.i1-IQ3_XXS.gguf b/gpt-oss-nemo-20b.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..436404d --- /dev/null +++ b/gpt-oss-nemo-20b.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab9b52fdb1e390744e0d8e5a9f9e3dcf9268e8bf0d9b0d675aaef215c10cdfa9 +size 12065514752 diff --git a/gpt-oss-nemo-20b.i1-IQ4_XS.gguf b/gpt-oss-nemo-20b.i1-IQ4_XS.gguf new file mode 100644 index 0000000..5fd21c0 --- /dev/null +++ b/gpt-oss-nemo-20b.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58c8dcee4598a83aa3ac13631cc1123af11d068e5808942cbf1fd5f796b86f20 +size 12096480512 diff --git a/gpt-oss-nemo-20b.i1-Q2_K.gguf b/gpt-oss-nemo-20b.i1-Q2_K.gguf new file mode 100644 index 0000000..9498ade --- /dev/null +++ b/gpt-oss-nemo-20b.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:828f56d89da8cc9f6ef85150c4fb9dff73f693247c31e2eca5e7b2a7bd271c74 +size 12065514752 diff --git a/gpt-oss-nemo-20b.i1-Q2_K_S.gguf b/gpt-oss-nemo-20b.i1-Q2_K_S.gguf new file mode 100644 index 0000000..86a499d --- /dev/null +++ b/gpt-oss-nemo-20b.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13c329599bbfa6e8bf9825215389901e0c4155b46d126b76dae7f064c5609d9e +size 12136293632 diff --git a/gpt-oss-nemo-20b.i1-Q3_K_L.gguf b/gpt-oss-nemo-20b.i1-Q3_K_L.gguf new file mode 100644 index 0000000..2ebe647 --- /dev/null +++ b/gpt-oss-nemo-20b.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7211d0d75ab0817c2d643752f4e40e50287dd3831581cbd9cc8c28159aa229e9 +size 13335110912 diff --git a/gpt-oss-nemo-20b.i1-Q3_K_M.gguf b/gpt-oss-nemo-20b.i1-Q3_K_M.gguf new file mode 100644 index 0000000..29b3a0f --- /dev/null +++ b/gpt-oss-nemo-20b.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2976c41497f0c1c7c7cd533ee0b722ef84e59bb7ff9715995906e6f249750547 +size 12916151552 diff --git a/gpt-oss-nemo-20b.i1-Q3_K_S.gguf b/gpt-oss-nemo-20b.i1-Q3_K_S.gguf new file mode 100644 index 0000000..5e1b089 --- /dev/null +++ b/gpt-oss-nemo-20b.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e260122ce67ddea29d3281fa8a5a880d8abcebba6be099de49002614f3cdeb6 +size 12061091072 diff --git a/gpt-oss-nemo-20b.i1-Q4_0.gguf b/gpt-oss-nemo-20b.i1-Q4_0.gguf new file mode 100644 index 0000000..7b2202a --- /dev/null +++ b/gpt-oss-nemo-20b.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf9d32a3a06d863bf3db949a096a1c24bde3c3255fdad4c44b0e2c5080309061 +size 12148458752 diff --git a/gpt-oss-nemo-20b.i1-Q4_1.gguf b/gpt-oss-nemo-20b.i1-Q4_1.gguf new file mode 100644 index 0000000..33e3639 --- /dev/null +++ b/gpt-oss-nemo-20b.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb46dbde21e35ad631e22cf86e4ff12ae6c7d6e6ebd670c83da66ed683fda503 +size 13369094912 diff --git a/gpt-oss-nemo-20b.i1-Q4_K_M.gguf b/gpt-oss-nemo-20b.i1-Q4_K_M.gguf new file mode 100644 index 0000000..b3c1987 --- /dev/null +++ b/gpt-oss-nemo-20b.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b648efebadb4dffc6b4cb151d7f3bae5c4a02863507b4a1b8e01f3a1fd33acd +size 15805137152 diff --git a/gpt-oss-nemo-20b.i1-Q4_K_S.gguf b/gpt-oss-nemo-20b.i1-Q4_K_S.gguf new file mode 100644 index 0000000..1397682 --- /dev/null +++ b/gpt-oss-nemo-20b.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03a6545ef50cf11a34c580606f836df44d2d3a6873fdaf345b3ca868a7797c2a +size 14654243072 diff --git a/gpt-oss-nemo-20b.i1-Q5_K_M.gguf b/gpt-oss-nemo-20b.i1-Q5_K_M.gguf new file mode 100644 index 0000000..5c3a327 --- /dev/null +++ b/gpt-oss-nemo-20b.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0cf92e3988b7985d1a09f5c04bc64eb2e11ff5f6c1ff063e3fa3ea52be718f8a +size 16893062912 diff --git a/gpt-oss-nemo-20b.i1-Q5_K_S.gguf b/gpt-oss-nemo-20b.i1-Q5_K_S.gguf new file mode 100644 index 0000000..3105d6b --- /dev/null +++ b/gpt-oss-nemo-20b.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce50a32deb53c998cd164453d18bfe695127d0e0121297f7e619c0e07c1704f4 +size 15892205312 diff --git a/gpt-oss-nemo-20b.i1-Q6_K.gguf b/gpt-oss-nemo-20b.i1-Q6_K.gguf new file mode 100644 index 0000000..f617254 --- /dev/null +++ b/gpt-oss-nemo-20b.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5de77d1988ea637b8edb65043fe26d63644acba51def66bc471e6d7bf9147a93 +size 22193345792 diff --git a/gpt-oss-nemo-20b.imatrix.gguf b/gpt-oss-nemo-20b.imatrix.gguf new file mode 100644 index 0000000..2fe74bd --- /dev/null +++ b/gpt-oss-nemo-20b.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e817b016f05abf01e3914e17aebfccac75642e7f2f1108b20946f4c5fab329e +size 28079776