commit 65ac4e2cc45610094654dcbddd3d042a804a96cb Author: ModelHub XC Date: Sat May 2 13:51:18 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/Disctil-Qwen3-1.7B-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..100a478 --- /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 +Disctil-Qwen3-1.7B.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +Disctil-Qwen3-1.7B.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Disctil-Qwen3-1.7B.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Disctil-Qwen3-1.7B.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Disctil-Qwen3-1.7B.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Disctil-Qwen3-1.7B.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Disctil-Qwen3-1.7B.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Disctil-Qwen3-1.7B.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Disctil-Qwen3-1.7B.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Disctil-Qwen3-1.7B.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Disctil-Qwen3-1.7B.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Disctil-Qwen3-1.7B.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Disctil-Qwen3-1.7B.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Disctil-Qwen3-1.7B.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Disctil-Qwen3-1.7B.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Disctil-Qwen3-1.7B.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Disctil-Qwen3-1.7B.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Disctil-Qwen3-1.7B.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Disctil-Qwen3-1.7B.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Disctil-Qwen3-1.7B.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Disctil-Qwen3-1.7B.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Disctil-Qwen3-1.7B.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Disctil-Qwen3-1.7B.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Disctil-Qwen3-1.7B.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Disctil-Qwen3-1.7B.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Disctil-Qwen3-1.7B.i1-IQ1_M.gguf b/Disctil-Qwen3-1.7B.i1-IQ1_M.gguf new file mode 100644 index 0000000..11d926a --- /dev/null +++ b/Disctil-Qwen3-1.7B.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ec352f53382b6429525742166f29b9a3a4459def7e6474d1a19fc9c2901ea73 +size 645895008 diff --git a/Disctil-Qwen3-1.7B.i1-IQ1_S.gguf b/Disctil-Qwen3-1.7B.i1-IQ1_S.gguf new file mode 100644 index 0000000..3ce81fc --- /dev/null +++ b/Disctil-Qwen3-1.7B.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2752ba58fad854de5873054a37ff13207a8055248147e5de7b951b40e6e82eb5 +size 617878368 diff --git a/Disctil-Qwen3-1.7B.i1-IQ2_M.gguf b/Disctil-Qwen3-1.7B.i1-IQ2_M.gguf new file mode 100644 index 0000000..276e012 --- /dev/null +++ b/Disctil-Qwen3-1.7B.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de0780bc745eaac4fb8b26227e88d87b005f4c7c24de5c0e6a0b7808ead48849 +size 828885856 diff --git a/Disctil-Qwen3-1.7B.i1-IQ2_S.gguf b/Disctil-Qwen3-1.7B.i1-IQ2_S.gguf new file mode 100644 index 0000000..708362e --- /dev/null +++ b/Disctil-Qwen3-1.7B.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fbd7714aae011e8469c39ab0d91732462d67d47f1d1021346c3ab355f50c258a +size 791530336 diff --git a/Disctil-Qwen3-1.7B.i1-IQ2_XS.gguf b/Disctil-Qwen3-1.7B.i1-IQ2_XS.gguf new file mode 100644 index 0000000..34325a4 --- /dev/null +++ b/Disctil-Qwen3-1.7B.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d357418eb96fa3f0ea0485d5133e2a4cfa472467dadd9fd0158f72e099c9223d +size 733614944 diff --git a/Disctil-Qwen3-1.7B.i1-IQ2_XXS.gguf b/Disctil-Qwen3-1.7B.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..a581d64 --- /dev/null +++ b/Disctil-Qwen3-1.7B.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6e9427648180e4cc7f40361527d1b6090ea3104485637a416dcad323382d0f1 +size 692589408 diff --git a/Disctil-Qwen3-1.7B.i1-IQ3_M.gguf b/Disctil-Qwen3-1.7B.i1-IQ3_M.gguf new file mode 100644 index 0000000..ab62151 --- /dev/null +++ b/Disctil-Qwen3-1.7B.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57c593a9e6f7b58ddbba455ab871bb7fe1c46e6f986c80b3d52089a6fdc329b9 +size 1029366624 diff --git a/Disctil-Qwen3-1.7B.i1-IQ3_S.gguf b/Disctil-Qwen3-1.7B.i1-IQ3_S.gguf new file mode 100644 index 0000000..be6da72 --- /dev/null +++ b/Disctil-Qwen3-1.7B.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df43937940d7f01d198045c8b77f01a1b624fc3b29d599f9759d460b2b51bef4 +size 1000956768 diff --git a/Disctil-Qwen3-1.7B.i1-IQ3_XS.gguf b/Disctil-Qwen3-1.7B.i1-IQ3_XS.gguf new file mode 100644 index 0000000..4119bbd --- /dev/null +++ b/Disctil-Qwen3-1.7B.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa7f7050377e4f266dcf3b363e18698f7abd523f751f52c8481c7d2d41e5ee8a +size 967926624 diff --git a/Disctil-Qwen3-1.7B.i1-IQ3_XXS.gguf b/Disctil-Qwen3-1.7B.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..fb51513 --- /dev/null +++ b/Disctil-Qwen3-1.7B.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb50e1020a129b7083fd6c0bbf77853227876f0146e86f4ba7e86b7601527dc2 +size 888064864 diff --git a/Disctil-Qwen3-1.7B.i1-IQ4_NL.gguf b/Disctil-Qwen3-1.7B.i1-IQ4_NL.gguf new file mode 100644 index 0000000..078c959 --- /dev/null +++ b/Disctil-Qwen3-1.7B.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2925286a33a6714555928776dd73ddd9594045e6c748f4d1843ef5357bb884cd +size 1229454176 diff --git a/Disctil-Qwen3-1.7B.i1-IQ4_XS.gguf b/Disctil-Qwen3-1.7B.i1-IQ4_XS.gguf new file mode 100644 index 0000000..9e4b267 --- /dev/null +++ b/Disctil-Qwen3-1.7B.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c533db5a35af816c5a4438d89971871736e3406292d3d3a0d4c6f100d35e3c0 +size 1175690080 diff --git a/Disctil-Qwen3-1.7B.i1-Q2_K.gguf b/Disctil-Qwen3-1.7B.i1-Q2_K.gguf new file mode 100644 index 0000000..a5c989f --- /dev/null +++ b/Disctil-Qwen3-1.7B.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:401fbe13c3f93435e92d0507c8727646a1409d9ff58561403c15720c08975204 +size 879897440 diff --git a/Disctil-Qwen3-1.7B.i1-Q2_K_S.gguf b/Disctil-Qwen3-1.7B.i1-Q2_K_S.gguf new file mode 100644 index 0000000..c79e0a7 --- /dev/null +++ b/Disctil-Qwen3-1.7B.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f71eaeaf51f052fd883317581d24dd2f7bd0dab5ea8b8eefb255c20a7b0eb3fe +size 835070816 diff --git a/Disctil-Qwen3-1.7B.i1-Q3_K_L.gguf b/Disctil-Qwen3-1.7B.i1-Q3_K_L.gguf new file mode 100644 index 0000000..f746917 --- /dev/null +++ b/Disctil-Qwen3-1.7B.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e9e19863bb04bd5efa69905f86057c8f518f7d503957edabfc8b7728fd7a439 +size 1137206112 diff --git a/Disctil-Qwen3-1.7B.i1-Q3_K_M.gguf b/Disctil-Qwen3-1.7B.i1-Q3_K_M.gguf new file mode 100644 index 0000000..4517fcf --- /dev/null +++ b/Disctil-Qwen3-1.7B.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7d0ab93ac79cb6838784ca57782bb294aaa2fce01d674a52aacd9ed6805c574 +size 1073242976 diff --git a/Disctil-Qwen3-1.7B.i1-Q3_K_S.gguf b/Disctil-Qwen3-1.7B.i1-Q3_K_S.gguf new file mode 100644 index 0000000..90673e5 --- /dev/null +++ b/Disctil-Qwen3-1.7B.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42cec9e7392d3504e68b7a902094443b97b2bc5476954b1cb37f9b7b2ca3746e +size 1000956768 diff --git a/Disctil-Qwen3-1.7B.i1-Q4_0.gguf b/Disctil-Qwen3-1.7B.i1-Q4_0.gguf new file mode 100644 index 0000000..ddb656b --- /dev/null +++ b/Disctil-Qwen3-1.7B.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97f6aba5c87b3083422db48a5b60b2e40c6c86996a721e3b4caecc19e4ba3de2 +size 1231813472 diff --git a/Disctil-Qwen3-1.7B.i1-Q4_1.gguf b/Disctil-Qwen3-1.7B.i1-Q4_1.gguf new file mode 100644 index 0000000..3df04e5 --- /dev/null +++ b/Disctil-Qwen3-1.7B.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:773e56a508e1f6f4f89d096dfc679e3c82ff724f67ef62fb340e4e45417be214 +size 1336982368 diff --git a/Disctil-Qwen3-1.7B.i1-Q4_K_M.gguf b/Disctil-Qwen3-1.7B.i1-Q4_K_M.gguf new file mode 100644 index 0000000..c0b8ccd --- /dev/null +++ b/Disctil-Qwen3-1.7B.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b6b8cad94377514f2d29b5c2ed7dec73dd41a1339ec3ec26cd48a2eb7dd7915 +size 1282440032 diff --git a/Disctil-Qwen3-1.7B.i1-Q4_K_S.gguf b/Disctil-Qwen3-1.7B.i1-Q4_K_S.gguf new file mode 100644 index 0000000..5c2e5b3 --- /dev/null +++ b/Disctil-Qwen3-1.7B.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01479f3d7ced697e8a44d3482a775b9ceb85a93ae2047d49347aad9caae44dfa +size 1235221344 diff --git a/Disctil-Qwen3-1.7B.i1-Q5_K_M.gguf b/Disctil-Qwen3-1.7B.i1-Q5_K_M.gguf new file mode 100644 index 0000000..86fa96a --- /dev/null +++ b/Disctil-Qwen3-1.7B.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:119fbbd153f83680b451507eff9ef13e14c8fd3a2d3453297457c7aab817291b +size 1471806304 diff --git a/Disctil-Qwen3-1.7B.i1-Q5_K_S.gguf b/Disctil-Qwen3-1.7B.i1-Q5_K_S.gguf new file mode 100644 index 0000000..5668e6c --- /dev/null +++ b/Disctil-Qwen3-1.7B.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e644f17270b0da378cedf3a85e020778aa8967b9fd59bce1e1a6c33a650d8fca +size 1444510560 diff --git a/Disctil-Qwen3-1.7B.i1-Q6_K.gguf b/Disctil-Qwen3-1.7B.i1-Q6_K.gguf new file mode 100644 index 0000000..e404945 --- /dev/null +++ b/Disctil-Qwen3-1.7B.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:321d6a278aecad1c73a9cb6a314013d689a381ee1c5c4c48a97df6ef211ef6cf +size 1673007968 diff --git a/Disctil-Qwen3-1.7B.imatrix.gguf b/Disctil-Qwen3-1.7B.imatrix.gguf new file mode 100644 index 0000000..cb4559e --- /dev/null +++ b/Disctil-Qwen3-1.7B.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8489a237cd46ab30e793c1d4cb14ef1b3fe7484b92f4daddae7a9335c85952a +size 2094560 diff --git a/README.md b/README.md new file mode 100644 index 0000000..75d2abf --- /dev/null +++ b/README.md @@ -0,0 +1,93 @@ +--- +base_model: reaperdoesntknow/Disctil-Qwen3-1.7B +language: +- en +library_name: transformers +model_name: Disctil-Qwen3-1.7B +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- generated_from_trainer +- sft +- trl +- convergentintel +- edge +- distillation +- knowledge-distillation +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/reaperdoesntknow/Disctil-Qwen3-1.7B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Disctil-Qwen3-1.7B-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Disctil-Qwen3-1.7B-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/Disctil-Qwen3-1.7B-i1-GGUF/resolve/main/Disctil-Qwen3-1.7B.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/Disctil-Qwen3-1.7B-i1-GGUF/resolve/main/Disctil-Qwen3-1.7B.i1-IQ1_S.gguf) | i1-IQ1_S | 0.7 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Disctil-Qwen3-1.7B-i1-GGUF/resolve/main/Disctil-Qwen3-1.7B.i1-IQ1_M.gguf) | i1-IQ1_M | 0.7 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Disctil-Qwen3-1.7B-i1-GGUF/resolve/main/Disctil-Qwen3-1.7B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Disctil-Qwen3-1.7B-i1-GGUF/resolve/main/Disctil-Qwen3-1.7B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Disctil-Qwen3-1.7B-i1-GGUF/resolve/main/Disctil-Qwen3-1.7B.i1-IQ2_S.gguf) | i1-IQ2_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Disctil-Qwen3-1.7B-i1-GGUF/resolve/main/Disctil-Qwen3-1.7B.i1-IQ2_M.gguf) | i1-IQ2_M | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Disctil-Qwen3-1.7B-i1-GGUF/resolve/main/Disctil-Qwen3-1.7B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 0.9 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Disctil-Qwen3-1.7B-i1-GGUF/resolve/main/Disctil-Qwen3-1.7B.i1-Q2_K.gguf) | i1-Q2_K | 1.0 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Disctil-Qwen3-1.7B-i1-GGUF/resolve/main/Disctil-Qwen3-1.7B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Disctil-Qwen3-1.7B-i1-GGUF/resolve/main/Disctil-Qwen3-1.7B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/Disctil-Qwen3-1.7B-i1-GGUF/resolve/main/Disctil-Qwen3-1.7B.i1-IQ3_S.gguf) | i1-IQ3_S | 1.1 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Disctil-Qwen3-1.7B-i1-GGUF/resolve/main/Disctil-Qwen3-1.7B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 1.1 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Disctil-Qwen3-1.7B-i1-GGUF/resolve/main/Disctil-Qwen3-1.7B.i1-IQ3_M.gguf) | i1-IQ3_M | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/Disctil-Qwen3-1.7B-i1-GGUF/resolve/main/Disctil-Qwen3-1.7B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 1.2 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Disctil-Qwen3-1.7B-i1-GGUF/resolve/main/Disctil-Qwen3-1.7B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 1.2 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Disctil-Qwen3-1.7B-i1-GGUF/resolve/main/Disctil-Qwen3-1.7B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/Disctil-Qwen3-1.7B-i1-GGUF/resolve/main/Disctil-Qwen3-1.7B.i1-IQ4_NL.gguf) | i1-IQ4_NL | 1.3 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Disctil-Qwen3-1.7B-i1-GGUF/resolve/main/Disctil-Qwen3-1.7B.i1-Q4_0.gguf) | i1-Q4_0 | 1.3 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Disctil-Qwen3-1.7B-i1-GGUF/resolve/main/Disctil-Qwen3-1.7B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 1.3 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Disctil-Qwen3-1.7B-i1-GGUF/resolve/main/Disctil-Qwen3-1.7B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 1.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Disctil-Qwen3-1.7B-i1-GGUF/resolve/main/Disctil-Qwen3-1.7B.i1-Q4_1.gguf) | i1-Q4_1 | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/Disctil-Qwen3-1.7B-i1-GGUF/resolve/main/Disctil-Qwen3-1.7B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Disctil-Qwen3-1.7B-i1-GGUF/resolve/main/Disctil-Qwen3-1.7B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Disctil-Qwen3-1.7B-i1-GGUF/resolve/main/Disctil-Qwen3-1.7B.i1-Q6_K.gguf) | i1-Q6_K | 1.8 | 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. + +