commit 9de1354b08c255e41e624ab750fe038705baf901 Author: ModelHub XC Date: Mon Apr 20 02:41:54 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/Cetus-Qwen3_4B-GeneralThought-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..b6397a2 --- /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 +imatrix.dat filter=lfs diff=lfs merge=lfs -text +Cetus-Qwen3_4B-GeneralThought.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Cetus-Qwen3_4B-GeneralThought.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Cetus-Qwen3_4B-GeneralThought.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Cetus-Qwen3_4B-GeneralThought.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Cetus-Qwen3_4B-GeneralThought.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Cetus-Qwen3_4B-GeneralThought.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Cetus-Qwen3_4B-GeneralThought.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Cetus-Qwen3_4B-GeneralThought.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Cetus-Qwen3_4B-GeneralThought.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Cetus-Qwen3_4B-GeneralThought.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Cetus-Qwen3_4B-GeneralThought.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Cetus-Qwen3_4B-GeneralThought.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Cetus-Qwen3_4B-GeneralThought.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Cetus-Qwen3_4B-GeneralThought.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Cetus-Qwen3_4B-GeneralThought.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Cetus-Qwen3_4B-GeneralThought.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Cetus-Qwen3_4B-GeneralThought.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Cetus-Qwen3_4B-GeneralThought.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Cetus-Qwen3_4B-GeneralThought.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Cetus-Qwen3_4B-GeneralThought.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Cetus-Qwen3_4B-GeneralThought.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Cetus-Qwen3_4B-GeneralThought.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Cetus-Qwen3_4B-GeneralThought.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Cetus-Qwen3_4B-GeneralThought.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Cetus-Qwen3_4B-GeneralThought.i1-IQ1_M.gguf b/Cetus-Qwen3_4B-GeneralThought.i1-IQ1_M.gguf new file mode 100644 index 0000000..e5e7820 --- /dev/null +++ b/Cetus-Qwen3_4B-GeneralThought.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab21c2916b2b03c8606017f0a1dddb07256bf2826d153dec24a2d7bfda49e928 +size 1127019136 diff --git a/Cetus-Qwen3_4B-GeneralThought.i1-IQ1_S.gguf b/Cetus-Qwen3_4B-GeneralThought.i1-IQ1_S.gguf new file mode 100644 index 0000000..0282db2 --- /dev/null +++ b/Cetus-Qwen3_4B-GeneralThought.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d140f30ab0e47106acddc1ba26496ee6aaa2f1fd51c76e87e01333ca489198b +size 1055257216 diff --git a/Cetus-Qwen3_4B-GeneralThought.i1-IQ2_M.gguf b/Cetus-Qwen3_4B-GeneralThought.i1-IQ2_M.gguf new file mode 100644 index 0000000..29e725b --- /dev/null +++ b/Cetus-Qwen3_4B-GeneralThought.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:309184f29b5ed31ed248709c420f22461eed85ec275cf8b8e6970ffabaff186d +size 1512985216 diff --git a/Cetus-Qwen3_4B-GeneralThought.i1-IQ2_S.gguf b/Cetus-Qwen3_4B-GeneralThought.i1-IQ2_S.gguf new file mode 100644 index 0000000..8b98966 --- /dev/null +++ b/Cetus-Qwen3_4B-GeneralThought.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:086f08249984e7f518deb7deefb0450943dcf3903d1e3cc90dbafef853ba60d0 +size 1417302656 diff --git a/Cetus-Qwen3_4B-GeneralThought.i1-IQ2_XS.gguf b/Cetus-Qwen3_4B-GeneralThought.i1-IQ2_XS.gguf new file mode 100644 index 0000000..352dac9 --- /dev/null +++ b/Cetus-Qwen3_4B-GeneralThought.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0851e31745c63be72e88ebb706f4f220f41d4ce71f6bf7a50fb510b3bf0ea23 +size 1354101376 diff --git a/Cetus-Qwen3_4B-GeneralThought.i1-IQ2_XXS.gguf b/Cetus-Qwen3_4B-GeneralThought.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..99e807f --- /dev/null +++ b/Cetus-Qwen3_4B-GeneralThought.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:464fae30ba1e09b8b6c12903d40670050e436f9a3f5d79189c242e6c6b8dff27 +size 1246622336 diff --git a/Cetus-Qwen3_4B-GeneralThought.i1-IQ3_M.gguf b/Cetus-Qwen3_4B-GeneralThought.i1-IQ3_M.gguf new file mode 100644 index 0000000..dc017b7 --- /dev/null +++ b/Cetus-Qwen3_4B-GeneralThought.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca1e0fa09b9188b590cc718f5f1169ceeac1f679de9be39d8c423f9054bb5798 +size 1962897536 diff --git a/Cetus-Qwen3_4B-GeneralThought.i1-IQ3_S.gguf b/Cetus-Qwen3_4B-GeneralThought.i1-IQ3_S.gguf new file mode 100644 index 0000000..405306b --- /dev/null +++ b/Cetus-Qwen3_4B-GeneralThought.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b816534875b90e0d7f3ce3ef7e1445499fda172dc720fc36c4263aa804bd69a1 +size 1899532416 diff --git a/Cetus-Qwen3_4B-GeneralThought.i1-IQ3_XS.gguf b/Cetus-Qwen3_4B-GeneralThought.i1-IQ3_XS.gguf new file mode 100644 index 0000000..1b2d135 --- /dev/null +++ b/Cetus-Qwen3_4B-GeneralThought.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:efafaba64c009e35696e811b6974e2f9fdeef2dec3965025ae7a21e6c81b222b +size 1814376576 diff --git a/Cetus-Qwen3_4B-GeneralThought.i1-IQ3_XXS.gguf b/Cetus-Qwen3_4B-GeneralThought.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..573eedd --- /dev/null +++ b/Cetus-Qwen3_4B-GeneralThought.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6aea739efee271dfa0a100003ba2ad3959914133f51bafb29aaa4487d4ac8eef +size 1670189696 diff --git a/Cetus-Qwen3_4B-GeneralThought.i1-IQ4_NL.gguf b/Cetus-Qwen3_4B-GeneralThought.i1-IQ4_NL.gguf new file mode 100644 index 0000000..d26a87d --- /dev/null +++ b/Cetus-Qwen3_4B-GeneralThought.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36180de6c2b60c51559ccb0d87f5daf29774b0dffa513cde97ebef508f22cd34 +size 2381344896 diff --git a/Cetus-Qwen3_4B-GeneralThought.i1-IQ4_XS.gguf b/Cetus-Qwen3_4B-GeneralThought.i1-IQ4_XS.gguf new file mode 100644 index 0000000..b7d43ff --- /dev/null +++ b/Cetus-Qwen3_4B-GeneralThought.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07bc9e27733b31d6ca9bb288bfbca849dcc1c97471bdebc03ad7681445f3d923 +size 2270752896 diff --git a/Cetus-Qwen3_4B-GeneralThought.i1-Q2_K.gguf b/Cetus-Qwen3_4B-GeneralThought.i1-Q2_K.gguf new file mode 100644 index 0000000..6d81ce2 --- /dev/null +++ b/Cetus-Qwen3_4B-GeneralThought.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba5180288d4b2acd089fbe3a56c4698ce36a6f9ceb91390b674e41965f6f9935 +size 1669501056 diff --git a/Cetus-Qwen3_4B-GeneralThought.i1-Q2_K_S.gguf b/Cetus-Qwen3_4B-GeneralThought.i1-Q2_K_S.gguf new file mode 100644 index 0000000..8f8a113 --- /dev/null +++ b/Cetus-Qwen3_4B-GeneralThought.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9732bc8c6831fc872ba8b258bc70df7ac59e90f9627f8c10ca239690b1cf3c4 +size 1563455616 diff --git a/Cetus-Qwen3_4B-GeneralThought.i1-Q3_K_L.gguf b/Cetus-Qwen3_4B-GeneralThought.i1-Q3_K_L.gguf new file mode 100644 index 0000000..684a1e4 --- /dev/null +++ b/Cetus-Qwen3_4B-GeneralThought.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7447edc030187dbcf900ab6ace48fec6ea573d1b2b667b729be2fe7afffbc51 +size 2239787136 diff --git a/Cetus-Qwen3_4B-GeneralThought.i1-Q3_K_M.gguf b/Cetus-Qwen3_4B-GeneralThought.i1-Q3_K_M.gguf new file mode 100644 index 0000000..26a1785 --- /dev/null +++ b/Cetus-Qwen3_4B-GeneralThought.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2db4b3243813c632b1008800208a7be0b19bbed3bceebe2d71af8e41ba0b0f61 +size 2075619456 diff --git a/Cetus-Qwen3_4B-GeneralThought.i1-Q3_K_S.gguf b/Cetus-Qwen3_4B-GeneralThought.i1-Q3_K_S.gguf new file mode 100644 index 0000000..11b79c1 --- /dev/null +++ b/Cetus-Qwen3_4B-GeneralThought.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e98a28109a24e41e7d27ed8e0adfaebc882a1c60f7c3f2f1b3793b6a91b42e45 +size 1886998656 diff --git a/Cetus-Qwen3_4B-GeneralThought.i1-Q4_0.gguf b/Cetus-Qwen3_4B-GeneralThought.i1-Q4_0.gguf new file mode 100644 index 0000000..02f9cc6 --- /dev/null +++ b/Cetus-Qwen3_4B-GeneralThought.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ebd8aa2a1c4ed30e213ce4b86b1ef953c60500d48e6a92a3b79ffe98c812c9f +size 2375774336 diff --git a/Cetus-Qwen3_4B-GeneralThought.i1-Q4_1.gguf b/Cetus-Qwen3_4B-GeneralThought.i1-Q4_1.gguf new file mode 100644 index 0000000..811ef5d --- /dev/null +++ b/Cetus-Qwen3_4B-GeneralThought.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:525f10e4dae203d270cdb9fa0a1fc9637b7cd80bb20ef9ee14fa477e02da7ff5 +size 2596630656 diff --git a/Cetus-Qwen3_4B-GeneralThought.i1-Q4_K_M.gguf b/Cetus-Qwen3_4B-GeneralThought.i1-Q4_K_M.gguf new file mode 100644 index 0000000..103b14d --- /dev/null +++ b/Cetus-Qwen3_4B-GeneralThought.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1681e31c0f2e2c040b8e630e9733f64edf3d8cebe2686bf9ed927b05fef11b68 +size 2497282176 diff --git a/Cetus-Qwen3_4B-GeneralThought.i1-Q4_K_S.gguf b/Cetus-Qwen3_4B-GeneralThought.i1-Q4_K_S.gguf new file mode 100644 index 0000000..d37d016 --- /dev/null +++ b/Cetus-Qwen3_4B-GeneralThought.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6a82b270683af6e1b3e49f8423e83a4d2e231deff7f987e7c60f6c4d00b3392 +size 2383310976 diff --git a/Cetus-Qwen3_4B-GeneralThought.i1-Q5_K_M.gguf b/Cetus-Qwen3_4B-GeneralThought.i1-Q5_K_M.gguf new file mode 100644 index 0000000..ab9daab --- /dev/null +++ b/Cetus-Qwen3_4B-GeneralThought.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ec7a4b1f333e921fd00787fa21e8b69f78e2524341ff458594aba98be21c3ec +size 2889515136 diff --git a/Cetus-Qwen3_4B-GeneralThought.i1-Q5_K_S.gguf b/Cetus-Qwen3_4B-GeneralThought.i1-Q5_K_S.gguf new file mode 100644 index 0000000..643c673 --- /dev/null +++ b/Cetus-Qwen3_4B-GeneralThought.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:765a542fafd02d4139ba55fdddb21b694deb51a042ece4376084da9a1eb6563c +size 2823712896 diff --git a/Cetus-Qwen3_4B-GeneralThought.i1-Q6_K.gguf b/Cetus-Qwen3_4B-GeneralThought.i1-Q6_K.gguf new file mode 100644 index 0000000..b013544 --- /dev/null +++ b/Cetus-Qwen3_4B-GeneralThought.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30ab3c7854be22baac121613259475f68109d44cfcf9167c8ba076bb09f9863d +size 3306262656 diff --git a/README.md b/README.md new file mode 100644 index 0000000..81cb52c --- /dev/null +++ b/README.md @@ -0,0 +1,88 @@ +--- +base_model: prithivMLmods/Cetus-Qwen3_4B-GeneralThought +datasets: +- GeneralReasoning/GeneralThought-430K +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- moe +- text-generation-inference +- code +- math +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/prithivMLmods/Cetus-Qwen3_4B-GeneralThought + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Cetus-Qwen3_4B-GeneralThought-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Cetus-Qwen3_4B-GeneralThought-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/Cetus-Qwen3_4B-GeneralThought-i1-GGUF/resolve/main/Cetus-Qwen3_4B-GeneralThought.i1-IQ1_S.gguf) | i1-IQ1_S | 1.2 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Cetus-Qwen3_4B-GeneralThought-i1-GGUF/resolve/main/Cetus-Qwen3_4B-GeneralThought.i1-IQ1_M.gguf) | i1-IQ1_M | 1.2 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Cetus-Qwen3_4B-GeneralThought-i1-GGUF/resolve/main/Cetus-Qwen3_4B-GeneralThought.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/Cetus-Qwen3_4B-GeneralThought-i1-GGUF/resolve/main/Cetus-Qwen3_4B-GeneralThought.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Cetus-Qwen3_4B-GeneralThought-i1-GGUF/resolve/main/Cetus-Qwen3_4B-GeneralThought.i1-IQ2_S.gguf) | i1-IQ2_S | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Cetus-Qwen3_4B-GeneralThought-i1-GGUF/resolve/main/Cetus-Qwen3_4B-GeneralThought.i1-IQ2_M.gguf) | i1-IQ2_M | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Cetus-Qwen3_4B-GeneralThought-i1-GGUF/resolve/main/Cetus-Qwen3_4B-GeneralThought.i1-Q2_K_S.gguf) | i1-Q2_K_S | 1.7 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Cetus-Qwen3_4B-GeneralThought-i1-GGUF/resolve/main/Cetus-Qwen3_4B-GeneralThought.i1-Q2_K.gguf) | i1-Q2_K | 1.8 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Cetus-Qwen3_4B-GeneralThought-i1-GGUF/resolve/main/Cetus-Qwen3_4B-GeneralThought.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Cetus-Qwen3_4B-GeneralThought-i1-GGUF/resolve/main/Cetus-Qwen3_4B-GeneralThought.i1-IQ3_XS.gguf) | i1-IQ3_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Cetus-Qwen3_4B-GeneralThought-i1-GGUF/resolve/main/Cetus-Qwen3_4B-GeneralThought.i1-Q3_K_S.gguf) | i1-Q3_K_S | 2.0 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Cetus-Qwen3_4B-GeneralThought-i1-GGUF/resolve/main/Cetus-Qwen3_4B-GeneralThought.i1-IQ3_S.gguf) | i1-IQ3_S | 2.0 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Cetus-Qwen3_4B-GeneralThought-i1-GGUF/resolve/main/Cetus-Qwen3_4B-GeneralThought.i1-IQ3_M.gguf) | i1-IQ3_M | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/Cetus-Qwen3_4B-GeneralThought-i1-GGUF/resolve/main/Cetus-Qwen3_4B-GeneralThought.i1-Q3_K_M.gguf) | i1-Q3_K_M | 2.2 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Cetus-Qwen3_4B-GeneralThought-i1-GGUF/resolve/main/Cetus-Qwen3_4B-GeneralThought.i1-Q3_K_L.gguf) | i1-Q3_K_L | 2.3 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Cetus-Qwen3_4B-GeneralThought-i1-GGUF/resolve/main/Cetus-Qwen3_4B-GeneralThought.i1-IQ4_XS.gguf) | i1-IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Cetus-Qwen3_4B-GeneralThought-i1-GGUF/resolve/main/Cetus-Qwen3_4B-GeneralThought.i1-Q4_0.gguf) | i1-Q4_0 | 2.5 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Cetus-Qwen3_4B-GeneralThought-i1-GGUF/resolve/main/Cetus-Qwen3_4B-GeneralThought.i1-IQ4_NL.gguf) | i1-IQ4_NL | 2.5 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Cetus-Qwen3_4B-GeneralThought-i1-GGUF/resolve/main/Cetus-Qwen3_4B-GeneralThought.i1-Q4_K_S.gguf) | i1-Q4_K_S | 2.5 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Cetus-Qwen3_4B-GeneralThought-i1-GGUF/resolve/main/Cetus-Qwen3_4B-GeneralThought.i1-Q4_K_M.gguf) | i1-Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Cetus-Qwen3_4B-GeneralThought-i1-GGUF/resolve/main/Cetus-Qwen3_4B-GeneralThought.i1-Q4_1.gguf) | i1-Q4_1 | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Cetus-Qwen3_4B-GeneralThought-i1-GGUF/resolve/main/Cetus-Qwen3_4B-GeneralThought.i1-Q5_K_S.gguf) | i1-Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Cetus-Qwen3_4B-GeneralThought-i1-GGUF/resolve/main/Cetus-Qwen3_4B-GeneralThought.i1-Q5_K_M.gguf) | i1-Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Cetus-Qwen3_4B-GeneralThought-i1-GGUF/resolve/main/Cetus-Qwen3_4B-GeneralThought.i1-Q6_K.gguf) | i1-Q6_K | 3.4 | 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/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..4afb183 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0fffdeca595f320957d0be5f9171d774c3c953dcc7b985b1c70fcc285bbc225 +size 3842209