commit e29be0058c8167bf66585a96a70b75813ae7e7df Author: ModelHub XC Date: Sat May 2 13:00:55 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/OctoThinker-3B-Short-Base-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..37633ac --- /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 +OctoThinker-3B-Short-Base.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +OctoThinker-3B-Short-Base.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +OctoThinker-3B-Short-Base.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +OctoThinker-3B-Short-Base.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +OctoThinker-3B-Short-Base.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +OctoThinker-3B-Short-Base.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +OctoThinker-3B-Short-Base.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +OctoThinker-3B-Short-Base.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +OctoThinker-3B-Short-Base.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +OctoThinker-3B-Short-Base.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +OctoThinker-3B-Short-Base.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +OctoThinker-3B-Short-Base.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +OctoThinker-3B-Short-Base.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +OctoThinker-3B-Short-Base.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +OctoThinker-3B-Short-Base.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OctoThinker-3B-Short-Base.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +OctoThinker-3B-Short-Base.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OctoThinker-3B-Short-Base.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OctoThinker-3B-Short-Base.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +OctoThinker-3B-Short-Base.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +OctoThinker-3B-Short-Base.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OctoThinker-3B-Short-Base.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OctoThinker-3B-Short-Base.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OctoThinker-3B-Short-Base.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OctoThinker-3B-Short-Base.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/OctoThinker-3B-Short-Base.i1-IQ1_M.gguf b/OctoThinker-3B-Short-Base.i1-IQ1_M.gguf new file mode 100644 index 0000000..8576029 --- /dev/null +++ b/OctoThinker-3B-Short-Base.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a660c83652b473925309067f6cba2f6876434f1f0bca3df2ee0d20a34aaf8c9 +size 924188512 diff --git a/OctoThinker-3B-Short-Base.i1-IQ1_S.gguf b/OctoThinker-3B-Short-Base.i1-IQ1_S.gguf new file mode 100644 index 0000000..bb85df8 --- /dev/null +++ b/OctoThinker-3B-Short-Base.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8d1320dc88c73372ce44b76f727303d2b282cd435d5ba23139ffdd03b8697b7 +size 868155232 diff --git a/OctoThinker-3B-Short-Base.i1-IQ2_M.gguf b/OctoThinker-3B-Short-Base.i1-IQ2_M.gguf new file mode 100644 index 0000000..050998b --- /dev/null +++ b/OctoThinker-3B-Short-Base.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6117f1ec6ea285442e3ce6743c8c77e783e1ba59ab60cefeca451fa707e841e +size 1229029216 diff --git a/OctoThinker-3B-Short-Base.i1-IQ2_S.gguf b/OctoThinker-3B-Short-Base.i1-IQ2_S.gguf new file mode 100644 index 0000000..c829d9c --- /dev/null +++ b/OctoThinker-3B-Short-Base.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f148ca0962df07ec89aeb721de784d4dc94fcc701944ccbf9a17d15e485f51c +size 1154318176 diff --git a/OctoThinker-3B-Short-Base.i1-IQ2_XS.gguf b/OctoThinker-3B-Short-Base.i1-IQ2_XS.gguf new file mode 100644 index 0000000..ce11662 --- /dev/null +++ b/OctoThinker-3B-Short-Base.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1097ac1d15bd36633d256ad915e3174f8ba079066bf5d8b0ae3ec1ddbf399e4c +size 1100545888 diff --git a/OctoThinker-3B-Short-Base.i1-IQ2_XXS.gguf b/OctoThinker-3B-Short-Base.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..95b445f --- /dev/null +++ b/OctoThinker-3B-Short-Base.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d2b4faf899ee4511d76a0f05f038d48ff6f1a5782bc53753f580e3e6c3a96b1 +size 1017577312 diff --git a/OctoThinker-3B-Short-Base.i1-IQ3_M.gguf b/OctoThinker-3B-Short-Base.i1-IQ3_M.gguf new file mode 100644 index 0000000..fc12d16 --- /dev/null +++ b/OctoThinker-3B-Short-Base.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9faa90257b90650ca58f88859a3b905a7f30f50caad2cdb714fd4d21a6466732 +size 1599666016 diff --git a/OctoThinker-3B-Short-Base.i1-IQ3_S.gguf b/OctoThinker-3B-Short-Base.i1-IQ3_S.gguf new file mode 100644 index 0000000..29f4696 --- /dev/null +++ b/OctoThinker-3B-Short-Base.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8c9cbe75e269ea3818cde4e51354b70d928318dddfba4c9802b9dda90f1d739 +size 1542846304 diff --git a/OctoThinker-3B-Short-Base.i1-IQ3_XS.gguf b/OctoThinker-3B-Short-Base.i1-IQ3_XS.gguf new file mode 100644 index 0000000..92136f4 --- /dev/null +++ b/OctoThinker-3B-Short-Base.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36523eea8cb061f4a37916afcbcc5e8195e5dfb3d72eb39519464ed409eb5cc7 +size 1476786016 diff --git a/OctoThinker-3B-Short-Base.i1-IQ3_XXS.gguf b/OctoThinker-3B-Short-Base.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..fac65dd --- /dev/null +++ b/OctoThinker-3B-Short-Base.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25a3ff71be361e7fb64613671b07cefc7672f1f9d3ef3fbe12947d9d8fe42885 +size 1348763488 diff --git a/OctoThinker-3B-Short-Base.i1-IQ4_NL.gguf b/OctoThinker-3B-Short-Base.i1-IQ4_NL.gguf new file mode 100644 index 0000000..c179a13 --- /dev/null +++ b/OctoThinker-3B-Short-Base.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca8628d769b8e22dd40431cb7a5e4903501306f13d50041c65fff3db6849804d +size 1917187936 diff --git a/OctoThinker-3B-Short-Base.i1-IQ4_XS.gguf b/OctoThinker-3B-Short-Base.i1-IQ4_XS.gguf new file mode 100644 index 0000000..d4456da --- /dev/null +++ b/OctoThinker-3B-Short-Base.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71395144ae984228848e0cf802f290549f83e89af8f57e548f06eef9e70f36fa +size 1829107552 diff --git a/OctoThinker-3B-Short-Base.i1-Q2_K.gguf b/OctoThinker-3B-Short-Base.i1-Q2_K.gguf new file mode 100644 index 0000000..4fef3c1 --- /dev/null +++ b/OctoThinker-3B-Short-Base.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2434f5fa11fed4b6d2797f4b53c9f54e91bf4c3c2e84509dc94b198080cdffe3 +size 1363933024 diff --git a/OctoThinker-3B-Short-Base.i1-Q2_K_S.gguf b/OctoThinker-3B-Short-Base.i1-Q2_K_S.gguf new file mode 100644 index 0000000..6767759 --- /dev/null +++ b/OctoThinker-3B-Short-Base.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:548164fbc9048da9e6d2f30f212e08fca0d826fe229d9277354787cac9a24e51 +size 1274279776 diff --git a/OctoThinker-3B-Short-Base.i1-Q3_K_L.gguf b/OctoThinker-3B-Short-Base.i1-Q3_K_L.gguf new file mode 100644 index 0000000..27dced4 --- /dev/null +++ b/OctoThinker-3B-Short-Base.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de0a74de0c346ab0a6c68ca41c748d90a78c6f74d5e43ed000a671c1d27ba2f4 +size 1815344992 diff --git a/OctoThinker-3B-Short-Base.i1-Q3_K_M.gguf b/OctoThinker-3B-Short-Base.i1-Q3_K_M.gguf new file mode 100644 index 0000000..8cd0b61 --- /dev/null +++ b/OctoThinker-3B-Short-Base.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff403d502ee961d2d2c7896c6287918133c2ce43a8cd5e2bf15e47f14c52eeb5 +size 1687156576 diff --git a/OctoThinker-3B-Short-Base.i1-Q3_K_S.gguf b/OctoThinker-3B-Short-Base.i1-Q3_K_S.gguf new file mode 100644 index 0000000..a997b42 --- /dev/null +++ b/OctoThinker-3B-Short-Base.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a88eb9cd2fe4af09470861abf770bc168c181e96140816228a42002a385c80f2 +size 1542846304 diff --git a/OctoThinker-3B-Short-Base.i1-Q4_0.gguf b/OctoThinker-3B-Short-Base.i1-Q4_0.gguf new file mode 100644 index 0000000..248c800 --- /dev/null +++ b/OctoThinker-3B-Short-Base.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94f2c124813a91f1b182ea2db518e4c2a813d968082e1b42c60a9d949caf9fb3 +size 1921906528 diff --git a/OctoThinker-3B-Short-Base.i1-Q4_1.gguf b/OctoThinker-3B-Short-Base.i1-Q4_1.gguf new file mode 100644 index 0000000..a51adac --- /dev/null +++ b/OctoThinker-3B-Short-Base.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:220afa5c9c0376e94ea006074dc08c9be9ee103d365583938344b2367be90387 +size 2093348704 diff --git a/OctoThinker-3B-Short-Base.i1-Q4_K_M.gguf b/OctoThinker-3B-Short-Base.i1-Q4_K_M.gguf new file mode 100644 index 0000000..a581c78 --- /dev/null +++ b/OctoThinker-3B-Short-Base.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdfc5836dd2ca3f2d6f87fe77ac65445f9befcda9ce815735ff604d9fe764ef4 +size 2019374944 diff --git a/OctoThinker-3B-Short-Base.i1-Q4_K_S.gguf b/OctoThinker-3B-Short-Base.i1-Q4_K_S.gguf new file mode 100644 index 0000000..acdcfc4 --- /dev/null +++ b/OctoThinker-3B-Short-Base.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a9568791a67688e6e1b3549c122bbb9fc6d3fe6c27c8398aa39b17196150946 +size 1928197984 diff --git a/OctoThinker-3B-Short-Base.i1-Q5_K_M.gguf b/OctoThinker-3B-Short-Base.i1-Q5_K_M.gguf new file mode 100644 index 0000000..c545c51 --- /dev/null +++ b/OctoThinker-3B-Short-Base.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05583957f22c2dde1c95cbf515efb9f7c6be98bf2a72f873e9563f976c525e54 +size 2322151264 diff --git a/OctoThinker-3B-Short-Base.i1-Q5_K_S.gguf b/OctoThinker-3B-Short-Base.i1-Q5_K_S.gguf new file mode 100644 index 0000000..a48c50f --- /dev/null +++ b/OctoThinker-3B-Short-Base.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee6e8b595dfa454dd8e49c57df628ccd356059d2354b2bbea5a7b00644a4dc72 +size 2269509472 diff --git a/OctoThinker-3B-Short-Base.i1-Q6_K.gguf b/OctoThinker-3B-Short-Base.i1-Q6_K.gguf new file mode 100644 index 0000000..be80a15 --- /dev/null +++ b/OctoThinker-3B-Short-Base.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e91c4b7c3c464efc8e689f429f87a20609be091d5177a7a815f96a30b60cd4e +size 2643851104 diff --git a/OctoThinker-3B-Short-Base.imatrix.gguf b/OctoThinker-3B-Short-Base.imatrix.gguf new file mode 100644 index 0000000..c0055d4 --- /dev/null +++ b/OctoThinker-3B-Short-Base.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92ea867ba17ca2ae5ece6e369b44a527a199272147eed950c8691de8e97173f0 +size 3012064 diff --git a/README.md b/README.md new file mode 100644 index 0000000..08db47a --- /dev/null +++ b/README.md @@ -0,0 +1,88 @@ +--- +base_model: OctoThinker/OctoThinker-3B-Short-Base +datasets: +- OctoThinker/MegaMath-Web-Pro-Max +- LLM360/MegaMath +language: +- en +library_name: transformers +license: llama3.2 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/OctoThinker/OctoThinker-3B-Short-Base + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#OctoThinker-3B-Short-Base-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/OctoThinker-3B-Short-Base-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/OctoThinker-3B-Short-Base-i1-GGUF/resolve/main/OctoThinker-3B-Short-Base.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/OctoThinker-3B-Short-Base-i1-GGUF/resolve/main/OctoThinker-3B-Short-Base.i1-IQ1_S.gguf) | i1-IQ1_S | 1.0 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/OctoThinker-3B-Short-Base-i1-GGUF/resolve/main/OctoThinker-3B-Short-Base.i1-IQ1_M.gguf) | i1-IQ1_M | 1.0 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/OctoThinker-3B-Short-Base-i1-GGUF/resolve/main/OctoThinker-3B-Short-Base.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/OctoThinker-3B-Short-Base-i1-GGUF/resolve/main/OctoThinker-3B-Short-Base.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/OctoThinker-3B-Short-Base-i1-GGUF/resolve/main/OctoThinker-3B-Short-Base.i1-IQ2_S.gguf) | i1-IQ2_S | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/OctoThinker-3B-Short-Base-i1-GGUF/resolve/main/OctoThinker-3B-Short-Base.i1-IQ2_M.gguf) | i1-IQ2_M | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/OctoThinker-3B-Short-Base-i1-GGUF/resolve/main/OctoThinker-3B-Short-Base.i1-Q2_K_S.gguf) | i1-Q2_K_S | 1.4 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/OctoThinker-3B-Short-Base-i1-GGUF/resolve/main/OctoThinker-3B-Short-Base.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/OctoThinker-3B-Short-Base-i1-GGUF/resolve/main/OctoThinker-3B-Short-Base.i1-Q2_K.gguf) | i1-Q2_K | 1.5 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/OctoThinker-3B-Short-Base-i1-GGUF/resolve/main/OctoThinker-3B-Short-Base.i1-IQ3_XS.gguf) | i1-IQ3_XS | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/OctoThinker-3B-Short-Base-i1-GGUF/resolve/main/OctoThinker-3B-Short-Base.i1-IQ3_S.gguf) | i1-IQ3_S | 1.6 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/OctoThinker-3B-Short-Base-i1-GGUF/resolve/main/OctoThinker-3B-Short-Base.i1-Q3_K_S.gguf) | i1-Q3_K_S | 1.6 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/OctoThinker-3B-Short-Base-i1-GGUF/resolve/main/OctoThinker-3B-Short-Base.i1-IQ3_M.gguf) | i1-IQ3_M | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/OctoThinker-3B-Short-Base-i1-GGUF/resolve/main/OctoThinker-3B-Short-Base.i1-Q3_K_M.gguf) | i1-Q3_K_M | 1.8 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/OctoThinker-3B-Short-Base-i1-GGUF/resolve/main/OctoThinker-3B-Short-Base.i1-Q3_K_L.gguf) | i1-Q3_K_L | 1.9 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/OctoThinker-3B-Short-Base-i1-GGUF/resolve/main/OctoThinker-3B-Short-Base.i1-IQ4_XS.gguf) | i1-IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/OctoThinker-3B-Short-Base-i1-GGUF/resolve/main/OctoThinker-3B-Short-Base.i1-IQ4_NL.gguf) | i1-IQ4_NL | 2.0 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/OctoThinker-3B-Short-Base-i1-GGUF/resolve/main/OctoThinker-3B-Short-Base.i1-Q4_0.gguf) | i1-Q4_0 | 2.0 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/OctoThinker-3B-Short-Base-i1-GGUF/resolve/main/OctoThinker-3B-Short-Base.i1-Q4_K_S.gguf) | i1-Q4_K_S | 2.0 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/OctoThinker-3B-Short-Base-i1-GGUF/resolve/main/OctoThinker-3B-Short-Base.i1-Q4_K_M.gguf) | i1-Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/OctoThinker-3B-Short-Base-i1-GGUF/resolve/main/OctoThinker-3B-Short-Base.i1-Q4_1.gguf) | i1-Q4_1 | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/OctoThinker-3B-Short-Base-i1-GGUF/resolve/main/OctoThinker-3B-Short-Base.i1-Q5_K_S.gguf) | i1-Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/OctoThinker-3B-Short-Base-i1-GGUF/resolve/main/OctoThinker-3B-Short-Base.i1-Q5_K_M.gguf) | i1-Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/OctoThinker-3B-Short-Base-i1-GGUF/resolve/main/OctoThinker-3B-Short-Base.i1-Q6_K.gguf) | i1-Q6_K | 2.7 | 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. + +