commit 49f1915af3c5386cc3ad20a19b1cd301d360724b Author: ModelHub XC Date: Thu Apr 30 11:06:07 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/MicroThinker-3B-Preview-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..4500318 --- /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 +MicroThinker-3B-Preview.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +MicroThinker-3B-Preview.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +MicroThinker-3B-Preview.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +MicroThinker-3B-Preview.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +MicroThinker-3B-Preview.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +MicroThinker-3B-Preview.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +MicroThinker-3B-Preview.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +MicroThinker-3B-Preview.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +MicroThinker-3B-Preview.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +MicroThinker-3B-Preview.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +MicroThinker-3B-Preview.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +MicroThinker-3B-Preview.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +MicroThinker-3B-Preview.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MicroThinker-3B-Preview.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MicroThinker-3B-Preview.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +MicroThinker-3B-Preview.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MicroThinker-3B-Preview.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MicroThinker-3B-Preview.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +MicroThinker-3B-Preview.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +MicroThinker-3B-Preview.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MicroThinker-3B-Preview.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MicroThinker-3B-Preview.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MicroThinker-3B-Preview.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MicroThinker-3B-Preview.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MicroThinker-3B-Preview.i1-IQ1_M.gguf b/MicroThinker-3B-Preview.i1-IQ1_M.gguf new file mode 100644 index 0000000..e0fa43a --- /dev/null +++ b/MicroThinker-3B-Preview.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2814a2a14b6f9afe7402a5ff2439bdd47470ef6a0af928dc063445f3c7a55d8a +size 924192192 diff --git a/MicroThinker-3B-Preview.i1-IQ1_S.gguf b/MicroThinker-3B-Preview.i1-IQ1_S.gguf new file mode 100644 index 0000000..0bd7002 --- /dev/null +++ b/MicroThinker-3B-Preview.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd33d1358a33be13b47f2fa63249eb66e43b5374c9157baa1cb90f78a989fe37 +size 868158912 diff --git a/MicroThinker-3B-Preview.i1-IQ2_M.gguf b/MicroThinker-3B-Preview.i1-IQ2_M.gguf new file mode 100644 index 0000000..af68e70 --- /dev/null +++ b/MicroThinker-3B-Preview.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd1492bf5eb55c2ec2e9c66bf7c5cf5ef415921543db804c2f67bef1b006682f +size 1229032896 diff --git a/MicroThinker-3B-Preview.i1-IQ2_S.gguf b/MicroThinker-3B-Preview.i1-IQ2_S.gguf new file mode 100644 index 0000000..43a911a --- /dev/null +++ b/MicroThinker-3B-Preview.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:addd550e8914d7558ed64bd788f52d7f7c4888373c737cae353fa59c2d279c52 +size 1154321856 diff --git a/MicroThinker-3B-Preview.i1-IQ2_XS.gguf b/MicroThinker-3B-Preview.i1-IQ2_XS.gguf new file mode 100644 index 0000000..3ba38dc --- /dev/null +++ b/MicroThinker-3B-Preview.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1372acf46a7dadae9c5a71d1122ff4ddf9fdf69bb9b64847ff2e369c6d47456c +size 1100549568 diff --git a/MicroThinker-3B-Preview.i1-IQ2_XXS.gguf b/MicroThinker-3B-Preview.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..9920f8a --- /dev/null +++ b/MicroThinker-3B-Preview.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86f14090508a93ea62e792899143a36222ec6d652b21d678e7b97484b6d111a6 +size 1017580992 diff --git a/MicroThinker-3B-Preview.i1-IQ3_M.gguf b/MicroThinker-3B-Preview.i1-IQ3_M.gguf new file mode 100644 index 0000000..9ab2eb0 --- /dev/null +++ b/MicroThinker-3B-Preview.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:819cd2e075ecf16926eed664051691dcac001a4f9d179b02848b01300a867d75 +size 1599669696 diff --git a/MicroThinker-3B-Preview.i1-IQ3_S.gguf b/MicroThinker-3B-Preview.i1-IQ3_S.gguf new file mode 100644 index 0000000..8b4376d --- /dev/null +++ b/MicroThinker-3B-Preview.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59b2719ffde3e9c25e758d810c77188dc6c3b7dd9cdb72759bf5ab08e4b0ff19 +size 1542849984 diff --git a/MicroThinker-3B-Preview.i1-IQ3_XS.gguf b/MicroThinker-3B-Preview.i1-IQ3_XS.gguf new file mode 100644 index 0000000..3b16a13 --- /dev/null +++ b/MicroThinker-3B-Preview.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c6eabaa49aefbf80806a526d735d87a8f2c07292c7115e5548763662d2e5e75 +size 1476789696 diff --git a/MicroThinker-3B-Preview.i1-IQ3_XXS.gguf b/MicroThinker-3B-Preview.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..c412ed5 --- /dev/null +++ b/MicroThinker-3B-Preview.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93b99ea92639a8446ee5b97835dfc6e82aaae7b6e09b86fff5fc786497cb388e +size 1348767168 diff --git a/MicroThinker-3B-Preview.i1-IQ4_NL.gguf b/MicroThinker-3B-Preview.i1-IQ4_NL.gguf new file mode 100644 index 0000000..83ff50b --- /dev/null +++ b/MicroThinker-3B-Preview.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bff7e95818b9355781acb18c15744072eb1c26788b7af3c468e0d87484c857dc +size 1917191616 diff --git a/MicroThinker-3B-Preview.i1-IQ4_XS.gguf b/MicroThinker-3B-Preview.i1-IQ4_XS.gguf new file mode 100644 index 0000000..0bd1365 --- /dev/null +++ b/MicroThinker-3B-Preview.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3f85b58c5f1451c10a8c206ea6bf7adc8d02f7aa5ab80f4ef8a20dc3c7a15d9 +size 1829111232 diff --git a/MicroThinker-3B-Preview.i1-Q2_K.gguf b/MicroThinker-3B-Preview.i1-Q2_K.gguf new file mode 100644 index 0000000..e1809dc --- /dev/null +++ b/MicroThinker-3B-Preview.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b244e45467de905c4902a03cbb8736d051e7feefc6f0163cbdc5a789a87f7cc4 +size 1363936704 diff --git a/MicroThinker-3B-Preview.i1-Q2_K_S.gguf b/MicroThinker-3B-Preview.i1-Q2_K_S.gguf new file mode 100644 index 0000000..c93d6c4 --- /dev/null +++ b/MicroThinker-3B-Preview.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5225e6f9d54a142273d1926029a5b5bcd5ee3b0e938ee91c8c64eade9ef71dae +size 1274283456 diff --git a/MicroThinker-3B-Preview.i1-Q3_K_L.gguf b/MicroThinker-3B-Preview.i1-Q3_K_L.gguf new file mode 100644 index 0000000..1dc5554 --- /dev/null +++ b/MicroThinker-3B-Preview.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc5af0b284d861da9829c13370090586a091e47250e2189115b0fd6e28a8be3f +size 1815348672 diff --git a/MicroThinker-3B-Preview.i1-Q3_K_M.gguf b/MicroThinker-3B-Preview.i1-Q3_K_M.gguf new file mode 100644 index 0000000..ec1afde --- /dev/null +++ b/MicroThinker-3B-Preview.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85b791cfa7ec01c516abbd7ddc6fa7743aed518cecf098dbccbb36c61c272758 +size 1687160256 diff --git a/MicroThinker-3B-Preview.i1-Q3_K_S.gguf b/MicroThinker-3B-Preview.i1-Q3_K_S.gguf new file mode 100644 index 0000000..5098bfa --- /dev/null +++ b/MicroThinker-3B-Preview.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:383826057d3b7edc98373d45ecdb8e3fe32279e643f8f703bed407421c6687bb +size 1542849984 diff --git a/MicroThinker-3B-Preview.i1-Q4_0.gguf b/MicroThinker-3B-Preview.i1-Q4_0.gguf new file mode 100644 index 0000000..508f7e8 --- /dev/null +++ b/MicroThinker-3B-Preview.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7127b52fe0108ba2a6f7921e128c57fd803fdf307f99a328bd6416451ba30bf +size 1921910208 diff --git a/MicroThinker-3B-Preview.i1-Q4_1.gguf b/MicroThinker-3B-Preview.i1-Q4_1.gguf new file mode 100644 index 0000000..b04be38 --- /dev/null +++ b/MicroThinker-3B-Preview.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dde3c14b8ecc5a15be2cea04d84396403272246b592686992bf5fb2b99d09c36 +size 2093352384 diff --git a/MicroThinker-3B-Preview.i1-Q4_K_M.gguf b/MicroThinker-3B-Preview.i1-Q4_K_M.gguf new file mode 100644 index 0000000..d1c6acf --- /dev/null +++ b/MicroThinker-3B-Preview.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:835b04680bbd1a98c812f9304e80cf9770735f3c5bf0835ff854637ebb041e9a +size 2019378624 diff --git a/MicroThinker-3B-Preview.i1-Q4_K_S.gguf b/MicroThinker-3B-Preview.i1-Q4_K_S.gguf new file mode 100644 index 0000000..2e27f37 --- /dev/null +++ b/MicroThinker-3B-Preview.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1f3b73f96aba2c6cdcbe462b60e330c62a599de536294385e2b868cdabb73be +size 1928201664 diff --git a/MicroThinker-3B-Preview.i1-Q5_K_M.gguf b/MicroThinker-3B-Preview.i1-Q5_K_M.gguf new file mode 100644 index 0000000..b260877 --- /dev/null +++ b/MicroThinker-3B-Preview.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47cbe5ad5023c1e9ddd8a816c0e2af07adb282b9a6e5ec8094af3dea00d91037 +size 2322154944 diff --git a/MicroThinker-3B-Preview.i1-Q5_K_S.gguf b/MicroThinker-3B-Preview.i1-Q5_K_S.gguf new file mode 100644 index 0000000..e9b9d7b --- /dev/null +++ b/MicroThinker-3B-Preview.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a99394b08a882e58d7a280a851ded967023c4186c0ea82647656384cc937c76 +size 2269513152 diff --git a/MicroThinker-3B-Preview.i1-Q6_K.gguf b/MicroThinker-3B-Preview.i1-Q6_K.gguf new file mode 100644 index 0000000..3920dca --- /dev/null +++ b/MicroThinker-3B-Preview.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5501ea56292375cfd925059323bfa626ce4f11185e6974f41e464a445b9e9d4f +size 2643854784 diff --git a/README.md b/README.md new file mode 100644 index 0000000..9c8cee9 --- /dev/null +++ b/README.md @@ -0,0 +1,82 @@ +--- +base_model: huihui-ai/MicroThinker-3B-Preview +datasets: +- huihui-ai/FineQwQ-142k +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- llama3.2 +- abliterated +- uncensored +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/huihui-ai/MicroThinker-3B-Preview + + +static quants are available at https://huggingface.co/mradermacher/MicroThinker-3B-Preview-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/MicroThinker-3B-Preview-i1-GGUF/resolve/main/MicroThinker-3B-Preview.i1-IQ1_S.gguf) | i1-IQ1_S | 1.0 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/MicroThinker-3B-Preview-i1-GGUF/resolve/main/MicroThinker-3B-Preview.i1-IQ1_M.gguf) | i1-IQ1_M | 1.0 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/MicroThinker-3B-Preview-i1-GGUF/resolve/main/MicroThinker-3B-Preview.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/MicroThinker-3B-Preview-i1-GGUF/resolve/main/MicroThinker-3B-Preview.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/MicroThinker-3B-Preview-i1-GGUF/resolve/main/MicroThinker-3B-Preview.i1-IQ2_S.gguf) | i1-IQ2_S | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/MicroThinker-3B-Preview-i1-GGUF/resolve/main/MicroThinker-3B-Preview.i1-IQ2_M.gguf) | i1-IQ2_M | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/MicroThinker-3B-Preview-i1-GGUF/resolve/main/MicroThinker-3B-Preview.i1-Q2_K_S.gguf) | i1-Q2_K_S | 1.4 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/MicroThinker-3B-Preview-i1-GGUF/resolve/main/MicroThinker-3B-Preview.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/MicroThinker-3B-Preview-i1-GGUF/resolve/main/MicroThinker-3B-Preview.i1-Q2_K.gguf) | i1-Q2_K | 1.5 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/MicroThinker-3B-Preview-i1-GGUF/resolve/main/MicroThinker-3B-Preview.i1-IQ3_XS.gguf) | i1-IQ3_XS | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/MicroThinker-3B-Preview-i1-GGUF/resolve/main/MicroThinker-3B-Preview.i1-IQ3_S.gguf) | i1-IQ3_S | 1.6 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/MicroThinker-3B-Preview-i1-GGUF/resolve/main/MicroThinker-3B-Preview.i1-Q3_K_S.gguf) | i1-Q3_K_S | 1.6 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/MicroThinker-3B-Preview-i1-GGUF/resolve/main/MicroThinker-3B-Preview.i1-IQ3_M.gguf) | i1-IQ3_M | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/MicroThinker-3B-Preview-i1-GGUF/resolve/main/MicroThinker-3B-Preview.i1-Q3_K_M.gguf) | i1-Q3_K_M | 1.8 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/MicroThinker-3B-Preview-i1-GGUF/resolve/main/MicroThinker-3B-Preview.i1-Q3_K_L.gguf) | i1-Q3_K_L | 1.9 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/MicroThinker-3B-Preview-i1-GGUF/resolve/main/MicroThinker-3B-Preview.i1-IQ4_XS.gguf) | i1-IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/MicroThinker-3B-Preview-i1-GGUF/resolve/main/MicroThinker-3B-Preview.i1-IQ4_NL.gguf) | i1-IQ4_NL | 2.0 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/MicroThinker-3B-Preview-i1-GGUF/resolve/main/MicroThinker-3B-Preview.i1-Q4_0.gguf) | i1-Q4_0 | 2.0 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/MicroThinker-3B-Preview-i1-GGUF/resolve/main/MicroThinker-3B-Preview.i1-Q4_K_S.gguf) | i1-Q4_K_S | 2.0 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/MicroThinker-3B-Preview-i1-GGUF/resolve/main/MicroThinker-3B-Preview.i1-Q4_K_M.gguf) | i1-Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MicroThinker-3B-Preview-i1-GGUF/resolve/main/MicroThinker-3B-Preview.i1-Q4_1.gguf) | i1-Q4_1 | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/MicroThinker-3B-Preview-i1-GGUF/resolve/main/MicroThinker-3B-Preview.i1-Q5_K_S.gguf) | i1-Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/MicroThinker-3B-Preview-i1-GGUF/resolve/main/MicroThinker-3B-Preview.i1-Q5_K_M.gguf) | i1-Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/MicroThinker-3B-Preview-i1-GGUF/resolve/main/MicroThinker-3B-Preview.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. + + diff --git a/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..62d4992 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e6efa347ac31d04cc9a253f763e8a75b9446cee1ccb7a8ca4cc431ce7c44a93 +size 2988377