commit 132dea9eeec3c8e79032832faae35510a0e49fea Author: ModelHub XC Date: Fri May 22 10:28:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/PocketThinker-QwQ-3B-Instruct-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..bcf1d40 --- /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 +PocketThinker-QwQ-3B-Instruct.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +PocketThinker-QwQ-3B-Instruct.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +PocketThinker-QwQ-3B-Instruct.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +PocketThinker-QwQ-3B-Instruct.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +PocketThinker-QwQ-3B-Instruct.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +PocketThinker-QwQ-3B-Instruct.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +PocketThinker-QwQ-3B-Instruct.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +PocketThinker-QwQ-3B-Instruct.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +PocketThinker-QwQ-3B-Instruct.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +PocketThinker-QwQ-3B-Instruct.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +PocketThinker-QwQ-3B-Instruct.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +PocketThinker-QwQ-3B-Instruct.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +PocketThinker-QwQ-3B-Instruct.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +PocketThinker-QwQ-3B-Instruct.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +PocketThinker-QwQ-3B-Instruct.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +PocketThinker-QwQ-3B-Instruct.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +PocketThinker-QwQ-3B-Instruct.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +PocketThinker-QwQ-3B-Instruct.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +PocketThinker-QwQ-3B-Instruct.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +PocketThinker-QwQ-3B-Instruct.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +PocketThinker-QwQ-3B-Instruct.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +PocketThinker-QwQ-3B-Instruct.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +PocketThinker-QwQ-3B-Instruct.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +PocketThinker-QwQ-3B-Instruct.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/PocketThinker-QwQ-3B-Instruct.i1-IQ1_M.gguf b/PocketThinker-QwQ-3B-Instruct.i1-IQ1_M.gguf new file mode 100644 index 0000000..2b27197 --- /dev/null +++ b/PocketThinker-QwQ-3B-Instruct.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd8424f5eac9c812ac63242be510b210ce80faa111e311e69e637fbe2c1c19d6 +size 850027168 diff --git a/PocketThinker-QwQ-3B-Instruct.i1-IQ1_S.gguf b/PocketThinker-QwQ-3B-Instruct.i1-IQ1_S.gguf new file mode 100644 index 0000000..679adec --- /dev/null +++ b/PocketThinker-QwQ-3B-Instruct.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44c323598bc67d55f0610dab20789e4203bc50f22fbe4288aeef0cbd9ce31077 +size 791093920 diff --git a/PocketThinker-QwQ-3B-Instruct.i1-IQ2_M.gguf b/PocketThinker-QwQ-3B-Instruct.i1-IQ2_M.gguf new file mode 100644 index 0000000..87f9215 --- /dev/null +++ b/PocketThinker-QwQ-3B-Instruct.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:697ea43638fccee08ccb3822e37b5a741bef4164859f09d96028881f25f0b104 +size 1140515488 diff --git a/PocketThinker-QwQ-3B-Instruct.i1-IQ2_S.gguf b/PocketThinker-QwQ-3B-Instruct.i1-IQ2_S.gguf new file mode 100644 index 0000000..ee74667 --- /dev/null +++ b/PocketThinker-QwQ-3B-Instruct.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f20919ff2ccfd63418aaf3230bbd3a04b5df68e8d6a4be9d11e8fb8f04a7e91 +size 1061937824 diff --git a/PocketThinker-QwQ-3B-Instruct.i1-IQ2_XS.gguf b/PocketThinker-QwQ-3B-Instruct.i1-IQ2_XS.gguf new file mode 100644 index 0000000..82f7015 --- /dev/null +++ b/PocketThinker-QwQ-3B-Instruct.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b83dd9cf03a1fdb4fd0a1ceed2c781e335bd4526077d826d9046a05a4076b65c +size 1031545504 diff --git a/PocketThinker-QwQ-3B-Instruct.i1-IQ2_XXS.gguf b/PocketThinker-QwQ-3B-Instruct.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..c431771 --- /dev/null +++ b/PocketThinker-QwQ-3B-Instruct.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4accd785b75f7477048ef4fd730f7b3fb462a677badcaf887dfc70a5ff3876a0 +size 948249248 diff --git a/PocketThinker-QwQ-3B-Instruct.i1-IQ3_M.gguf b/PocketThinker-QwQ-3B-Instruct.i1-IQ3_M.gguf new file mode 100644 index 0000000..279148e --- /dev/null +++ b/PocketThinker-QwQ-3B-Instruct.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3088efa50cefd665e414be70e6c429ea1f5c4f304e1f128a376896bb13142f40 +size 1488894624 diff --git a/PocketThinker-QwQ-3B-Instruct.i1-IQ3_S.gguf b/PocketThinker-QwQ-3B-Instruct.i1-IQ3_S.gguf new file mode 100644 index 0000000..37610b9 --- /dev/null +++ b/PocketThinker-QwQ-3B-Instruct.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba095e95d6ba7df7158cca66a97554e09249ba5ba3dddddde830ad79b7b0e4d9 +size 1456863904 diff --git a/PocketThinker-QwQ-3B-Instruct.i1-IQ3_XS.gguf b/PocketThinker-QwQ-3B-Instruct.i1-IQ3_XS.gguf new file mode 100644 index 0000000..7fa66ed --- /dev/null +++ b/PocketThinker-QwQ-3B-Instruct.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7147345b7f429d5a5ba476581aa297c5398458b39b6ce1f0ebb0197e45b8c72f +size 1391835808 diff --git a/PocketThinker-QwQ-3B-Instruct.i1-IQ3_XXS.gguf b/PocketThinker-QwQ-3B-Instruct.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..04f9ebf --- /dev/null +++ b/PocketThinker-QwQ-3B-Instruct.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aaf803e557be8d56654b741d3de0e3b6054187fbcd13d7a3b35c0fcad923d720 +size 1282826912 diff --git a/PocketThinker-QwQ-3B-Instruct.i1-IQ4_NL.gguf b/PocketThinker-QwQ-3B-Instruct.i1-IQ4_NL.gguf new file mode 100644 index 0000000..5857207 --- /dev/null +++ b/PocketThinker-QwQ-3B-Instruct.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68bef6e5a0220be09bc4c64acd858214b40526a89eb9303438cc79b5a0b4814a +size 1825208992 diff --git a/PocketThinker-QwQ-3B-Instruct.i1-IQ4_XS.gguf b/PocketThinker-QwQ-3B-Instruct.i1-IQ4_XS.gguf new file mode 100644 index 0000000..689a4b0 --- /dev/null +++ b/PocketThinker-QwQ-3B-Instruct.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4a907e4aa9ccedcce44f2cea0dd61744356b324831bf6080af771dcc8467cad +size 1739094688 diff --git a/PocketThinker-QwQ-3B-Instruct.i1-Q2_K.gguf b/PocketThinker-QwQ-3B-Instruct.i1-Q2_K.gguf new file mode 100644 index 0000000..1536e5c --- /dev/null +++ b/PocketThinker-QwQ-3B-Instruct.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a5a225245b033a7089452f1e8f7e8017878baa6987d35d555a7d7adc0c07c73 +size 1274755744 diff --git a/PocketThinker-QwQ-3B-Instruct.i1-Q2_K_S.gguf b/PocketThinker-QwQ-3B-Instruct.i1-Q2_K_S.gguf new file mode 100644 index 0000000..3172f51 --- /dev/null +++ b/PocketThinker-QwQ-3B-Instruct.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abd435ef363e0bf612d65a43e81482c7668538e352541b3b0e4b2654e212bcad +size 1198127776 diff --git a/PocketThinker-QwQ-3B-Instruct.i1-Q3_K_L.gguf b/PocketThinker-QwQ-3B-Instruct.i1-Q3_K_L.gguf new file mode 100644 index 0000000..f477721 --- /dev/null +++ b/PocketThinker-QwQ-3B-Instruct.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1762b54fb523d91c8f39396b0dda5757c239a5b295ecad59b940020ce50c631 +size 1707391648 diff --git a/PocketThinker-QwQ-3B-Instruct.i1-Q3_K_M.gguf b/PocketThinker-QwQ-3B-Instruct.i1-Q3_K_M.gguf new file mode 100644 index 0000000..058b5ba --- /dev/null +++ b/PocketThinker-QwQ-3B-Instruct.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:923272dd083a791550dd82af009e0cb4c4f6ec926646c2b7e31fb9987ba081f3 +size 1590475424 diff --git a/PocketThinker-QwQ-3B-Instruct.i1-Q3_K_S.gguf b/PocketThinker-QwQ-3B-Instruct.i1-Q3_K_S.gguf new file mode 100644 index 0000000..b50ef8f --- /dev/null +++ b/PocketThinker-QwQ-3B-Instruct.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8abfe0ac277b299fa7133a2809cc4f2f037b1609747170fa307761b486067047 +size 1454357152 diff --git a/PocketThinker-QwQ-3B-Instruct.i1-Q4_0.gguf b/PocketThinker-QwQ-3B-Instruct.i1-Q4_0.gguf new file mode 100644 index 0000000..c59d7df --- /dev/null +++ b/PocketThinker-QwQ-3B-Instruct.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cffa1d7866afa25503e1aaf691676fa8093d50161743a6c447ac7582194ebe06 +size 1828485792 diff --git a/PocketThinker-QwQ-3B-Instruct.i1-Q4_1.gguf b/PocketThinker-QwQ-3B-Instruct.i1-Q4_1.gguf new file mode 100644 index 0000000..2c0bd11 --- /dev/null +++ b/PocketThinker-QwQ-3B-Instruct.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54da36ee4b3d109828131d20d8d8c8202ade965518f1b5a9fc13c3261fcb485d +size 1996257952 diff --git a/PocketThinker-QwQ-3B-Instruct.i1-Q4_K_M.gguf b/PocketThinker-QwQ-3B-Instruct.i1-Q4_K_M.gguf new file mode 100644 index 0000000..c7fb3d2 --- /dev/null +++ b/PocketThinker-QwQ-3B-Instruct.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4d2831884572ecd1a860e4bee81a6ccad992a3b966db3d187c85a6ef0c506fe +size 1929902752 diff --git a/PocketThinker-QwQ-3B-Instruct.i1-Q4_K_S.gguf b/PocketThinker-QwQ-3B-Instruct.i1-Q4_K_S.gguf new file mode 100644 index 0000000..7a13bd1 --- /dev/null +++ b/PocketThinker-QwQ-3B-Instruct.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f777c99403454a42de13056939610e8357871fae4499523aeaf20fabc363dfa9 +size 1834384032 diff --git a/PocketThinker-QwQ-3B-Instruct.i1-Q5_K_M.gguf b/PocketThinker-QwQ-3B-Instruct.i1-Q5_K_M.gguf new file mode 100644 index 0000000..2bf9143 --- /dev/null +++ b/PocketThinker-QwQ-3B-Instruct.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c106146c293ddf7b8de7a5ee78e24609b84b104e71371b9cbec4878292bdbe7 +size 2224814752 diff --git a/PocketThinker-QwQ-3B-Instruct.i1-Q5_K_S.gguf b/PocketThinker-QwQ-3B-Instruct.i1-Q5_K_S.gguf new file mode 100644 index 0000000..6909469 --- /dev/null +++ b/PocketThinker-QwQ-3B-Instruct.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1872ece5d695b92abfae73c6ab67e95ab4abc1a7974aa74e6519c68690e84bb4 +size 2169666208 diff --git a/PocketThinker-QwQ-3B-Instruct.i1-Q6_K.gguf b/PocketThinker-QwQ-3B-Instruct.i1-Q6_K.gguf new file mode 100644 index 0000000..6275455 --- /dev/null +++ b/PocketThinker-QwQ-3B-Instruct.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8301d1e9990cedc0bbef74997e6a65d0b05adeaaee78480a2627f3ae37542ba7 +size 2538158752 diff --git a/README.md b/README.md new file mode 100644 index 0000000..7a5d871 --- /dev/null +++ b/README.md @@ -0,0 +1,98 @@ +--- +base_model: prithivMLmods/PocketThinker-QwQ-3B-Instruct +datasets: +- amphora/QwQ-LongCoT-130K +- amphora/QwQ-LongCoT-130K-2 +- amphora/verfiable-25k +- amphora/m-math500 +language: +- en +- zh +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- Math +- Code +- Thinker +- Reasoning +- 3B +- QwQ +- Mini +- text-generation-inference +- SFT +- trl +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/prithivMLmods/PocketThinker-QwQ-3B-Instruct + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#PocketThinker-QwQ-3B-Instruct-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/PocketThinker-QwQ-3B-Instruct-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/PocketThinker-QwQ-3B-Instruct-i1-GGUF/resolve/main/PocketThinker-QwQ-3B-Instruct.i1-IQ1_S.gguf) | i1-IQ1_S | 0.9 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/PocketThinker-QwQ-3B-Instruct-i1-GGUF/resolve/main/PocketThinker-QwQ-3B-Instruct.i1-IQ1_M.gguf) | i1-IQ1_M | 1.0 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/PocketThinker-QwQ-3B-Instruct-i1-GGUF/resolve/main/PocketThinker-QwQ-3B-Instruct.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/PocketThinker-QwQ-3B-Instruct-i1-GGUF/resolve/main/PocketThinker-QwQ-3B-Instruct.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/PocketThinker-QwQ-3B-Instruct-i1-GGUF/resolve/main/PocketThinker-QwQ-3B-Instruct.i1-IQ2_S.gguf) | i1-IQ2_S | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/PocketThinker-QwQ-3B-Instruct-i1-GGUF/resolve/main/PocketThinker-QwQ-3B-Instruct.i1-IQ2_M.gguf) | i1-IQ2_M | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/PocketThinker-QwQ-3B-Instruct-i1-GGUF/resolve/main/PocketThinker-QwQ-3B-Instruct.i1-Q2_K_S.gguf) | i1-Q2_K_S | 1.3 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/PocketThinker-QwQ-3B-Instruct-i1-GGUF/resolve/main/PocketThinker-QwQ-3B-Instruct.i1-Q2_K.gguf) | i1-Q2_K | 1.4 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/PocketThinker-QwQ-3B-Instruct-i1-GGUF/resolve/main/PocketThinker-QwQ-3B-Instruct.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/PocketThinker-QwQ-3B-Instruct-i1-GGUF/resolve/main/PocketThinker-QwQ-3B-Instruct.i1-IQ3_XS.gguf) | i1-IQ3_XS | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/PocketThinker-QwQ-3B-Instruct-i1-GGUF/resolve/main/PocketThinker-QwQ-3B-Instruct.i1-Q3_K_S.gguf) | i1-Q3_K_S | 1.6 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/PocketThinker-QwQ-3B-Instruct-i1-GGUF/resolve/main/PocketThinker-QwQ-3B-Instruct.i1-IQ3_S.gguf) | i1-IQ3_S | 1.6 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/PocketThinker-QwQ-3B-Instruct-i1-GGUF/resolve/main/PocketThinker-QwQ-3B-Instruct.i1-IQ3_M.gguf) | i1-IQ3_M | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/PocketThinker-QwQ-3B-Instruct-i1-GGUF/resolve/main/PocketThinker-QwQ-3B-Instruct.i1-Q3_K_M.gguf) | i1-Q3_K_M | 1.7 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/PocketThinker-QwQ-3B-Instruct-i1-GGUF/resolve/main/PocketThinker-QwQ-3B-Instruct.i1-Q3_K_L.gguf) | i1-Q3_K_L | 1.8 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/PocketThinker-QwQ-3B-Instruct-i1-GGUF/resolve/main/PocketThinker-QwQ-3B-Instruct.i1-IQ4_XS.gguf) | i1-IQ4_XS | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/PocketThinker-QwQ-3B-Instruct-i1-GGUF/resolve/main/PocketThinker-QwQ-3B-Instruct.i1-IQ4_NL.gguf) | i1-IQ4_NL | 1.9 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/PocketThinker-QwQ-3B-Instruct-i1-GGUF/resolve/main/PocketThinker-QwQ-3B-Instruct.i1-Q4_0.gguf) | i1-Q4_0 | 1.9 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/PocketThinker-QwQ-3B-Instruct-i1-GGUF/resolve/main/PocketThinker-QwQ-3B-Instruct.i1-Q4_K_S.gguf) | i1-Q4_K_S | 1.9 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/PocketThinker-QwQ-3B-Instruct-i1-GGUF/resolve/main/PocketThinker-QwQ-3B-Instruct.i1-Q4_K_M.gguf) | i1-Q4_K_M | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/PocketThinker-QwQ-3B-Instruct-i1-GGUF/resolve/main/PocketThinker-QwQ-3B-Instruct.i1-Q4_1.gguf) | i1-Q4_1 | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/PocketThinker-QwQ-3B-Instruct-i1-GGUF/resolve/main/PocketThinker-QwQ-3B-Instruct.i1-Q5_K_S.gguf) | i1-Q5_K_S | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/PocketThinker-QwQ-3B-Instruct-i1-GGUF/resolve/main/PocketThinker-QwQ-3B-Instruct.i1-Q5_K_M.gguf) | i1-Q5_K_M | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/PocketThinker-QwQ-3B-Instruct-i1-GGUF/resolve/main/PocketThinker-QwQ-3B-Instruct.i1-Q6_K.gguf) | i1-Q6_K | 2.6 | 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..f39de49 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0481c3a92452a561ee4ba1b2e30308f9d234d36eff36aae3862bef7ae83bbb47 +size 3362977