commit e0e5c5b60ac25534ad86d74f655be12556ceb955 Author: ModelHub XC Date: Tue Jul 7 00:44:48 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/GPT-OSS-Code-Reasoning-20B-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2947a29 --- /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-Code-Reasoning-20B.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +GPT-OSS-Code-Reasoning-20B.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +GPT-OSS-Code-Reasoning-20B.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +GPT-OSS-Code-Reasoning-20B.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GPT-OSS-Code-Reasoning-20B.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +GPT-OSS-Code-Reasoning-20B.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GPT-OSS-Code-Reasoning-20B.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GPT-OSS-Code-Reasoning-20B.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +GPT-OSS-Code-Reasoning-20B.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +GPT-OSS-Code-Reasoning-20B.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +GPT-OSS-Code-Reasoning-20B.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GPT-OSS-Code-Reasoning-20B.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +GPT-OSS-Code-Reasoning-20B.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GPT-OSS-Code-Reasoning-20B.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +GPT-OSS-Code-Reasoning-20B.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +GPT-OSS-Code-Reasoning-20B.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +GPT-OSS-Code-Reasoning-20B.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GPT-OSS-Code-Reasoning-20B.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +GPT-OSS-Code-Reasoning-20B.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +GPT-OSS-Code-Reasoning-20B.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +GPT-OSS-Code-Reasoning-20B.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GPT-OSS-Code-Reasoning-20B.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +GPT-OSS-Code-Reasoning-20B.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +GPT-OSS-Code-Reasoning-20B.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/GPT-OSS-Code-Reasoning-20B.i1-IQ1_M.gguf b/GPT-OSS-Code-Reasoning-20B.i1-IQ1_M.gguf new file mode 100644 index 0000000..4400a78 --- /dev/null +++ b/GPT-OSS-Code-Reasoning-20B.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2571ec4dc89c336a827b63ecae880f22ea093ac96698df382aff75bc41da001a +size 12016853440 diff --git a/GPT-OSS-Code-Reasoning-20B.i1-IQ1_S.gguf b/GPT-OSS-Code-Reasoning-20B.i1-IQ1_S.gguf new file mode 100644 index 0000000..c7b3cc6 --- /dev/null +++ b/GPT-OSS-Code-Reasoning-20B.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71c6523ffc1c211fb79f6c07d3d58236745c4ec733a26656c462a7908cfd091b +size 12016853440 diff --git a/GPT-OSS-Code-Reasoning-20B.i1-IQ2_M.gguf b/GPT-OSS-Code-Reasoning-20B.i1-IQ2_M.gguf new file mode 100644 index 0000000..f8563f4 --- /dev/null +++ b/GPT-OSS-Code-Reasoning-20B.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:928ca9457c3cff11a328802d4d584ecf86144bcd58f6ae3dbdf5040b17f8210c +size 12065513920 diff --git a/GPT-OSS-Code-Reasoning-20B.i1-IQ2_S.gguf b/GPT-OSS-Code-Reasoning-20B.i1-IQ2_S.gguf new file mode 100644 index 0000000..93040b1 --- /dev/null +++ b/GPT-OSS-Code-Reasoning-20B.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0b301ca1378e75ba78ef242dd4e302004bb28925479c063229c18954df50f78 +size 12065513920 diff --git a/GPT-OSS-Code-Reasoning-20B.i1-IQ2_XS.gguf b/GPT-OSS-Code-Reasoning-20B.i1-IQ2_XS.gguf new file mode 100644 index 0000000..e30afe2 --- /dev/null +++ b/GPT-OSS-Code-Reasoning-20B.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1afa8d337878f47ef77608fbb9ef802717aca97c037488d2e872fe882e155677 +size 12025700800 diff --git a/GPT-OSS-Code-Reasoning-20B.i1-IQ2_XXS.gguf b/GPT-OSS-Code-Reasoning-20B.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..65bc2b4 --- /dev/null +++ b/GPT-OSS-Code-Reasoning-20B.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d5bdaf77552870e62fbbcd153a5dc7ddc45df22728c05e3db6764442a0a2697 +size 12016853440 diff --git a/GPT-OSS-Code-Reasoning-20B.i1-IQ3_M.gguf b/GPT-OSS-Code-Reasoning-20B.i1-IQ3_M.gguf new file mode 100644 index 0000000..36d8880 --- /dev/null +++ b/GPT-OSS-Code-Reasoning-20B.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a06a73156448e356775a560181b2811b2e7def283cfd8af6ece8693420f16714 +size 12202648000 diff --git a/GPT-OSS-Code-Reasoning-20B.i1-IQ3_S.gguf b/GPT-OSS-Code-Reasoning-20B.i1-IQ3_S.gguf new file mode 100644 index 0000000..1e91ecb --- /dev/null +++ b/GPT-OSS-Code-Reasoning-20B.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d23cd12a806969464f5460358ae01b8a3781da2071278aa361245d73adc9518e +size 12065513920 diff --git a/GPT-OSS-Code-Reasoning-20B.i1-IQ3_XS.gguf b/GPT-OSS-Code-Reasoning-20B.i1-IQ3_XS.gguf new file mode 100644 index 0000000..960c30e --- /dev/null +++ b/GPT-OSS-Code-Reasoning-20B.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91a15fda676499dc88c5c3b141837cc58bf5e1850c6b15ff5829dbf105b3c6f2 +size 12065513920 diff --git a/GPT-OSS-Code-Reasoning-20B.i1-IQ3_XXS.gguf b/GPT-OSS-Code-Reasoning-20B.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..b07bcc9 --- /dev/null +++ b/GPT-OSS-Code-Reasoning-20B.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a12f702626720b549fd562499cc6037e94e707a35963e552a4ccab0d5f262c8 +size 12065513920 diff --git a/GPT-OSS-Code-Reasoning-20B.i1-IQ4_XS.gguf b/GPT-OSS-Code-Reasoning-20B.i1-IQ4_XS.gguf new file mode 100644 index 0000000..c8fdda6 --- /dev/null +++ b/GPT-OSS-Code-Reasoning-20B.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:efd70fae7c861327687d7795b1b5cefd7dbe8e687dbe903fc331962650f3090f +size 12096479680 diff --git a/GPT-OSS-Code-Reasoning-20B.i1-Q2_K.gguf b/GPT-OSS-Code-Reasoning-20B.i1-Q2_K.gguf new file mode 100644 index 0000000..81201fc --- /dev/null +++ b/GPT-OSS-Code-Reasoning-20B.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9e614e26d3c2e23b4a4b51adbba3704bbdcaa842f4e9a5206e613d58a03b49f +size 12065513920 diff --git a/GPT-OSS-Code-Reasoning-20B.i1-Q2_K_S.gguf b/GPT-OSS-Code-Reasoning-20B.i1-Q2_K_S.gguf new file mode 100644 index 0000000..ff2fc97 --- /dev/null +++ b/GPT-OSS-Code-Reasoning-20B.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8086d208aa2503e68b5bc81901af42131e235b81b9209521ffb53b8c9858da4b +size 12136292800 diff --git a/GPT-OSS-Code-Reasoning-20B.i1-Q3_K_L.gguf b/GPT-OSS-Code-Reasoning-20B.i1-Q3_K_L.gguf new file mode 100644 index 0000000..d03495c --- /dev/null +++ b/GPT-OSS-Code-Reasoning-20B.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38ce31a00ae14294c8aa2af7dade48906f3e3adfa1b04c10e526eb581953b479 +size 13335110080 diff --git a/GPT-OSS-Code-Reasoning-20B.i1-Q3_K_M.gguf b/GPT-OSS-Code-Reasoning-20B.i1-Q3_K_M.gguf new file mode 100644 index 0000000..2899d04 --- /dev/null +++ b/GPT-OSS-Code-Reasoning-20B.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5198e1e61f98305eee03139f3878e488dc2666aabdbca2f55915cf79bd19435c +size 12916150720 diff --git a/GPT-OSS-Code-Reasoning-20B.i1-Q3_K_S.gguf b/GPT-OSS-Code-Reasoning-20B.i1-Q3_K_S.gguf new file mode 100644 index 0000000..92ba8a7 --- /dev/null +++ b/GPT-OSS-Code-Reasoning-20B.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:405b11d890c2a63b306811a496d9ac2b577fbb6a31ea1e4903d80591e3e2e5b8 +size 12061090240 diff --git a/GPT-OSS-Code-Reasoning-20B.i1-Q4_0.gguf b/GPT-OSS-Code-Reasoning-20B.i1-Q4_0.gguf new file mode 100644 index 0000000..bd67a4e --- /dev/null +++ b/GPT-OSS-Code-Reasoning-20B.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:417ad5fb4642c4c7e100b5f301d14fc7244c6e956845e18091f2f6862d851154 +size 12148457920 diff --git a/GPT-OSS-Code-Reasoning-20B.i1-Q4_1.gguf b/GPT-OSS-Code-Reasoning-20B.i1-Q4_1.gguf new file mode 100644 index 0000000..3f42810 --- /dev/null +++ b/GPT-OSS-Code-Reasoning-20B.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4cddf8235bff7a2562cae83489116e1fffc9e77c3c89ed6778fb03f04f908d81 +size 13369094080 diff --git a/GPT-OSS-Code-Reasoning-20B.i1-Q4_K_M.gguf b/GPT-OSS-Code-Reasoning-20B.i1-Q4_K_M.gguf new file mode 100644 index 0000000..e051fb6 --- /dev/null +++ b/GPT-OSS-Code-Reasoning-20B.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da59c3d1cd77d8d69e0ee4e14e113b192a9c477e28db9b1cba92256466a1b039 +size 15805136320 diff --git a/GPT-OSS-Code-Reasoning-20B.i1-Q4_K_S.gguf b/GPT-OSS-Code-Reasoning-20B.i1-Q4_K_S.gguf new file mode 100644 index 0000000..f5a6c2d --- /dev/null +++ b/GPT-OSS-Code-Reasoning-20B.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c61057ab2cb3d6bbb19fec5db1e0c2ea7aab55fd2ea71174a4909b0cf15c847a +size 14654242240 diff --git a/GPT-OSS-Code-Reasoning-20B.i1-Q5_K_M.gguf b/GPT-OSS-Code-Reasoning-20B.i1-Q5_K_M.gguf new file mode 100644 index 0000000..489a326 --- /dev/null +++ b/GPT-OSS-Code-Reasoning-20B.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db94c56d70b0ff8bca18a181917fda60613ce6eac5e51a038225dfa9c8749b68 +size 16893062080 diff --git a/GPT-OSS-Code-Reasoning-20B.i1-Q5_K_S.gguf b/GPT-OSS-Code-Reasoning-20B.i1-Q5_K_S.gguf new file mode 100644 index 0000000..627f457 --- /dev/null +++ b/GPT-OSS-Code-Reasoning-20B.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea88f2a7340d176e9db7a80ab528d47089d5d802e47c0f1249f78d0474e8f100 +size 15892204480 diff --git a/GPT-OSS-Code-Reasoning-20B.i1-Q6_K.gguf b/GPT-OSS-Code-Reasoning-20B.i1-Q6_K.gguf new file mode 100644 index 0000000..581d3ca --- /dev/null +++ b/GPT-OSS-Code-Reasoning-20B.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2885a65815880b6f56e331b7cbb45dc27e14a52a93e8a7142336df53cb7d3627 +size 22193344960 diff --git a/GPT-OSS-Code-Reasoning-20B.imatrix.gguf b/GPT-OSS-Code-Reasoning-20B.imatrix.gguf new file mode 100644 index 0000000..c1e52b5 --- /dev/null +++ b/GPT-OSS-Code-Reasoning-20B.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0d3efb0154f374ec27871f610543d00528fa259e37138ea54741923a80d16fd +size 28079776 diff --git a/README.md b/README.md new file mode 100644 index 0000000..3edd857 --- /dev/null +++ b/README.md @@ -0,0 +1,96 @@ +--- +base_model: GetSoloTech/GPT-OSS-Code-Reasoning-20B +datasets: +- nvidia/OpenCodeReasoning-2 +- GetSoloTech/Code-Reasoning +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- code-reasoning +- coding +- reasoning +- problem-solving +- algorithms +- python +- c++ +- competitive-programming +- vllm +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/GetSoloTech/GPT-OSS-Code-Reasoning-20B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#GPT-OSS-Code-Reasoning-20B-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/GPT-OSS-Code-Reasoning-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-Code-Reasoning-20B-i1-GGUF/resolve/main/GPT-OSS-Code-Reasoning-20B.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/GPT-OSS-Code-Reasoning-20B-i1-GGUF/resolve/main/GPT-OSS-Code-Reasoning-20B.i1-IQ1_M.gguf) | i1-IQ1_M | 12.1 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/GPT-OSS-Code-Reasoning-20B-i1-GGUF/resolve/main/GPT-OSS-Code-Reasoning-20B.i1-IQ1_S.gguf) | i1-IQ1_S | 12.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/GPT-OSS-Code-Reasoning-20B-i1-GGUF/resolve/main/GPT-OSS-Code-Reasoning-20B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 12.1 | | +| [GGUF](https://huggingface.co/mradermacher/GPT-OSS-Code-Reasoning-20B-i1-GGUF/resolve/main/GPT-OSS-Code-Reasoning-20B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 12.1 | | +| [GGUF](https://huggingface.co/mradermacher/GPT-OSS-Code-Reasoning-20B-i1-GGUF/resolve/main/GPT-OSS-Code-Reasoning-20B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 12.2 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/GPT-OSS-Code-Reasoning-20B-i1-GGUF/resolve/main/GPT-OSS-Code-Reasoning-20B.i1-IQ2_M.gguf) | i1-IQ2_M | 12.2 | | +| [GGUF](https://huggingface.co/mradermacher/GPT-OSS-Code-Reasoning-20B-i1-GGUF/resolve/main/GPT-OSS-Code-Reasoning-20B.i1-IQ2_S.gguf) | i1-IQ2_S | 12.2 | | +| [GGUF](https://huggingface.co/mradermacher/GPT-OSS-Code-Reasoning-20B-i1-GGUF/resolve/main/GPT-OSS-Code-Reasoning-20B.i1-IQ3_S.gguf) | i1-IQ3_S | 12.2 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/GPT-OSS-Code-Reasoning-20B-i1-GGUF/resolve/main/GPT-OSS-Code-Reasoning-20B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 12.2 | | +| [GGUF](https://huggingface.co/mradermacher/GPT-OSS-Code-Reasoning-20B-i1-GGUF/resolve/main/GPT-OSS-Code-Reasoning-20B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 12.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/GPT-OSS-Code-Reasoning-20B-i1-GGUF/resolve/main/GPT-OSS-Code-Reasoning-20B.i1-Q2_K.gguf) | i1-Q2_K | 12.2 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/GPT-OSS-Code-Reasoning-20B-i1-GGUF/resolve/main/GPT-OSS-Code-Reasoning-20B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 12.2 | | +| [GGUF](https://huggingface.co/mradermacher/GPT-OSS-Code-Reasoning-20B-i1-GGUF/resolve/main/GPT-OSS-Code-Reasoning-20B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 12.2 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/GPT-OSS-Code-Reasoning-20B-i1-GGUF/resolve/main/GPT-OSS-Code-Reasoning-20B.i1-Q4_0.gguf) | i1-Q4_0 | 12.2 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/GPT-OSS-Code-Reasoning-20B-i1-GGUF/resolve/main/GPT-OSS-Code-Reasoning-20B.i1-IQ3_M.gguf) | i1-IQ3_M | 12.3 | | +| [GGUF](https://huggingface.co/mradermacher/GPT-OSS-Code-Reasoning-20B-i1-GGUF/resolve/main/GPT-OSS-Code-Reasoning-20B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 13.0 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/GPT-OSS-Code-Reasoning-20B-i1-GGUF/resolve/main/GPT-OSS-Code-Reasoning-20B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 13.4 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/GPT-OSS-Code-Reasoning-20B-i1-GGUF/resolve/main/GPT-OSS-Code-Reasoning-20B.i1-Q4_1.gguf) | i1-Q4_1 | 13.5 | | +| [GGUF](https://huggingface.co/mradermacher/GPT-OSS-Code-Reasoning-20B-i1-GGUF/resolve/main/GPT-OSS-Code-Reasoning-20B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 14.8 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/GPT-OSS-Code-Reasoning-20B-i1-GGUF/resolve/main/GPT-OSS-Code-Reasoning-20B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 15.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GPT-OSS-Code-Reasoning-20B-i1-GGUF/resolve/main/GPT-OSS-Code-Reasoning-20B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 16.0 | | +| [GGUF](https://huggingface.co/mradermacher/GPT-OSS-Code-Reasoning-20B-i1-GGUF/resolve/main/GPT-OSS-Code-Reasoning-20B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 17.0 | | +| [GGUF](https://huggingface.co/mradermacher/GPT-OSS-Code-Reasoning-20B-i1-GGUF/resolve/main/GPT-OSS-Code-Reasoning-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. + +