commit eef3064a107cf3e02df6b54a2efafdc2624b7337 Author: ModelHub XC Date: Thu Apr 30 09:48:13 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/FluentlyQwen3-Coder-1.7B-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..b004f71 --- /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 +FluentlyQwen3-Coder-1.7B.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +FluentlyQwen3-Coder-1.7B.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +FluentlyQwen3-Coder-1.7B.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +FluentlyQwen3-Coder-1.7B.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +FluentlyQwen3-Coder-1.7B.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +FluentlyQwen3-Coder-1.7B.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +FluentlyQwen3-Coder-1.7B.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +FluentlyQwen3-Coder-1.7B.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +FluentlyQwen3-Coder-1.7B.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +FluentlyQwen3-Coder-1.7B.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +FluentlyQwen3-Coder-1.7B.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +FluentlyQwen3-Coder-1.7B.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +FluentlyQwen3-Coder-1.7B.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +FluentlyQwen3-Coder-1.7B.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +FluentlyQwen3-Coder-1.7B.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +FluentlyQwen3-Coder-1.7B.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +FluentlyQwen3-Coder-1.7B.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +FluentlyQwen3-Coder-1.7B.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +FluentlyQwen3-Coder-1.7B.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +FluentlyQwen3-Coder-1.7B.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +FluentlyQwen3-Coder-1.7B.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +FluentlyQwen3-Coder-1.7B.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +FluentlyQwen3-Coder-1.7B.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +FluentlyQwen3-Coder-1.7B.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +FluentlyQwen3-Coder-1.7B.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/FluentlyQwen3-Coder-1.7B.i1-IQ1_M.gguf b/FluentlyQwen3-Coder-1.7B.i1-IQ1_M.gguf new file mode 100644 index 0000000..281bdba --- /dev/null +++ b/FluentlyQwen3-Coder-1.7B.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dcebd6697dacc80b3bf6c291d4bb50205dc5d3cf2e59079345da3cd318fa2bf1 +size 645895424 diff --git a/FluentlyQwen3-Coder-1.7B.i1-IQ1_S.gguf b/FluentlyQwen3-Coder-1.7B.i1-IQ1_S.gguf new file mode 100644 index 0000000..e677ef9 --- /dev/null +++ b/FluentlyQwen3-Coder-1.7B.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70db526e05ce27650553c67c1f994278b0ba1f4649968c3861fd9046e9949f08 +size 617878784 diff --git a/FluentlyQwen3-Coder-1.7B.i1-IQ2_M.gguf b/FluentlyQwen3-Coder-1.7B.i1-IQ2_M.gguf new file mode 100644 index 0000000..c2ba0e8 --- /dev/null +++ b/FluentlyQwen3-Coder-1.7B.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b880c510d6c8a52a39b7afa642d9410964ecef9138e2b1181a00962dfbbcd1ce +size 828886272 diff --git a/FluentlyQwen3-Coder-1.7B.i1-IQ2_S.gguf b/FluentlyQwen3-Coder-1.7B.i1-IQ2_S.gguf new file mode 100644 index 0000000..f6c6fb7 --- /dev/null +++ b/FluentlyQwen3-Coder-1.7B.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0793dd8ad9b7820b8577c33c2ff74224ec99e4e88023202784606e8f7cd2492c +size 791530752 diff --git a/FluentlyQwen3-Coder-1.7B.i1-IQ2_XS.gguf b/FluentlyQwen3-Coder-1.7B.i1-IQ2_XS.gguf new file mode 100644 index 0000000..b5611c7 --- /dev/null +++ b/FluentlyQwen3-Coder-1.7B.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c085c3ca88472091b1f474be928e790308295abbca14ea44fdcb2a1335e5c4da +size 733615360 diff --git a/FluentlyQwen3-Coder-1.7B.i1-IQ2_XXS.gguf b/FluentlyQwen3-Coder-1.7B.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..4838a32 --- /dev/null +++ b/FluentlyQwen3-Coder-1.7B.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb41943be1ef5cb369f7db56ab4dc89ae77a1b4007ad0095398517dc158d7019 +size 692589824 diff --git a/FluentlyQwen3-Coder-1.7B.i1-IQ3_M.gguf b/FluentlyQwen3-Coder-1.7B.i1-IQ3_M.gguf new file mode 100644 index 0000000..f266f90 --- /dev/null +++ b/FluentlyQwen3-Coder-1.7B.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fc02876a554e565648b5dd059709fe60aeac4860ab6387d9d39ec6d8e719203 +size 1029367040 diff --git a/FluentlyQwen3-Coder-1.7B.i1-IQ3_S.gguf b/FluentlyQwen3-Coder-1.7B.i1-IQ3_S.gguf new file mode 100644 index 0000000..7d0fa01 --- /dev/null +++ b/FluentlyQwen3-Coder-1.7B.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bccef2777314d0cc68512b37c4ee261180ada94aa85cfbac6163b80c52b48dcf +size 1000957184 diff --git a/FluentlyQwen3-Coder-1.7B.i1-IQ3_XS.gguf b/FluentlyQwen3-Coder-1.7B.i1-IQ3_XS.gguf new file mode 100644 index 0000000..8733a6b --- /dev/null +++ b/FluentlyQwen3-Coder-1.7B.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:640d59eca9e048c6850a5c0cdcc77c244a3d574b6e47f3a163defced6b3856ab +size 967927040 diff --git a/FluentlyQwen3-Coder-1.7B.i1-IQ3_XXS.gguf b/FluentlyQwen3-Coder-1.7B.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..5fd7fd2 --- /dev/null +++ b/FluentlyQwen3-Coder-1.7B.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e622da96f35f47f20b3bf2facf34cb1f4c754bbcabf3b85256b41cddb620a6c +size 888065280 diff --git a/FluentlyQwen3-Coder-1.7B.i1-IQ4_NL.gguf b/FluentlyQwen3-Coder-1.7B.i1-IQ4_NL.gguf new file mode 100644 index 0000000..4991acd --- /dev/null +++ b/FluentlyQwen3-Coder-1.7B.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10acb1f2c2d62d4dda66410338829488d0a43e866f7815d04fcba234ac33b576 +size 1229454592 diff --git a/FluentlyQwen3-Coder-1.7B.i1-IQ4_XS.gguf b/FluentlyQwen3-Coder-1.7B.i1-IQ4_XS.gguf new file mode 100644 index 0000000..2d09d45 --- /dev/null +++ b/FluentlyQwen3-Coder-1.7B.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3623ee454dee7d33742a9e6e70f017bce009834d5ca9ba4d8a5a2a29c74b29d8 +size 1175690496 diff --git a/FluentlyQwen3-Coder-1.7B.i1-Q2_K.gguf b/FluentlyQwen3-Coder-1.7B.i1-Q2_K.gguf new file mode 100644 index 0000000..1e0f505 --- /dev/null +++ b/FluentlyQwen3-Coder-1.7B.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a474c93ac3a12660fd13368e255e610a487bb8975bbeaefa76df85fbc87744b +size 879897856 diff --git a/FluentlyQwen3-Coder-1.7B.i1-Q2_K_S.gguf b/FluentlyQwen3-Coder-1.7B.i1-Q2_K_S.gguf new file mode 100644 index 0000000..8f6c96d --- /dev/null +++ b/FluentlyQwen3-Coder-1.7B.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af5ea4c3c63dd179c78fa16dc1993951cdb46fd6deb1195e91a65bfecc49ec62 +size 835071232 diff --git a/FluentlyQwen3-Coder-1.7B.i1-Q3_K_L.gguf b/FluentlyQwen3-Coder-1.7B.i1-Q3_K_L.gguf new file mode 100644 index 0000000..85e9a22 --- /dev/null +++ b/FluentlyQwen3-Coder-1.7B.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08adf2c0e58c25fdb2bb251052ac7ca7b8ee1a2fe1d974bc93aa0e6063289b0f +size 1137206528 diff --git a/FluentlyQwen3-Coder-1.7B.i1-Q3_K_M.gguf b/FluentlyQwen3-Coder-1.7B.i1-Q3_K_M.gguf new file mode 100644 index 0000000..36cdfe4 --- /dev/null +++ b/FluentlyQwen3-Coder-1.7B.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0b2974461a0b4a0b25c9c1dba8c10f080c71a0d3fabdec45258e05df6dc3f0d +size 1073243392 diff --git a/FluentlyQwen3-Coder-1.7B.i1-Q3_K_S.gguf b/FluentlyQwen3-Coder-1.7B.i1-Q3_K_S.gguf new file mode 100644 index 0000000..81ca986 --- /dev/null +++ b/FluentlyQwen3-Coder-1.7B.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2cf7c1b1019be04b212ad56846349a59930a1bc4470de9f27f711d7363b7c2b4 +size 1000957184 diff --git a/FluentlyQwen3-Coder-1.7B.i1-Q4_0.gguf b/FluentlyQwen3-Coder-1.7B.i1-Q4_0.gguf new file mode 100644 index 0000000..188f40d --- /dev/null +++ b/FluentlyQwen3-Coder-1.7B.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b90bcd05c1be82e7baf58443afe6f0a069f20774c8a7b26620c9b22a3ca9881 +size 1231813888 diff --git a/FluentlyQwen3-Coder-1.7B.i1-Q4_1.gguf b/FluentlyQwen3-Coder-1.7B.i1-Q4_1.gguf new file mode 100644 index 0000000..8f150af --- /dev/null +++ b/FluentlyQwen3-Coder-1.7B.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35c9204ef002313708a6c13558f00bb2c52ceb1ef93ae00a66bf822c5be5eab6 +size 1336982784 diff --git a/FluentlyQwen3-Coder-1.7B.i1-Q4_K_M.gguf b/FluentlyQwen3-Coder-1.7B.i1-Q4_K_M.gguf new file mode 100644 index 0000000..b6ff121 --- /dev/null +++ b/FluentlyQwen3-Coder-1.7B.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e15788c5e6b4b1ab1a00b6a2e7432280abf9b3937f603e13d6f0d843c58a52eb +size 1282440448 diff --git a/FluentlyQwen3-Coder-1.7B.i1-Q4_K_S.gguf b/FluentlyQwen3-Coder-1.7B.i1-Q4_K_S.gguf new file mode 100644 index 0000000..fe2b137 --- /dev/null +++ b/FluentlyQwen3-Coder-1.7B.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96d3958b390a5db2acef5335f8a22a32d7b813ddec5ea136d1ca5341d14e9aeb +size 1235221760 diff --git a/FluentlyQwen3-Coder-1.7B.i1-Q5_K_M.gguf b/FluentlyQwen3-Coder-1.7B.i1-Q5_K_M.gguf new file mode 100644 index 0000000..802747a --- /dev/null +++ b/FluentlyQwen3-Coder-1.7B.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0fce11f4bc612c5730f7817dc11a72c29e1f5443f8b6dd6838edb0f8cbe4c3fe +size 1471806720 diff --git a/FluentlyQwen3-Coder-1.7B.i1-Q5_K_S.gguf b/FluentlyQwen3-Coder-1.7B.i1-Q5_K_S.gguf new file mode 100644 index 0000000..c0b224d --- /dev/null +++ b/FluentlyQwen3-Coder-1.7B.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2cf1eba31ea1500a05b09e85ea4282c5feebf7e5a807299d312237b013a6d015 +size 1444510976 diff --git a/FluentlyQwen3-Coder-1.7B.i1-Q6_K.gguf b/FluentlyQwen3-Coder-1.7B.i1-Q6_K.gguf new file mode 100644 index 0000000..1be26c1 --- /dev/null +++ b/FluentlyQwen3-Coder-1.7B.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9a66ea5001a52483d218b3c59c9a3e158a24c28edc491a244772145cb6afde8 +size 1673008384 diff --git a/FluentlyQwen3-Coder-1.7B.imatrix.gguf b/FluentlyQwen3-Coder-1.7B.imatrix.gguf new file mode 100644 index 0000000..656a196 --- /dev/null +++ b/FluentlyQwen3-Coder-1.7B.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e080eaf2c9c8a503baf7c4974d8a1f2f73205dcf8dcff352fc6eeaed60161cf7 +size 2094560 diff --git a/README.md b/README.md new file mode 100644 index 0000000..b56a9f7 --- /dev/null +++ b/README.md @@ -0,0 +1,101 @@ +--- +base_model: fluently/FluentlyQwen3-Coder-1.7B +datasets: +- nvidia/OpenCodeReasoning +language: +- en +- ru +- code +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- fluently +- fluently-lm +- qwen3 +- coder +- coding +- trained +- merged +- sft +- trl +- unsloth +- axolotl +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/fluently/FluentlyQwen3-Coder-1.7B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#FluentlyQwen3-Coder-1.7B-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/FluentlyQwen3-Coder-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/FluentlyQwen3-Coder-1.7B-i1-GGUF/resolve/main/FluentlyQwen3-Coder-1.7B.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/FluentlyQwen3-Coder-1.7B-i1-GGUF/resolve/main/FluentlyQwen3-Coder-1.7B.i1-IQ1_S.gguf) | i1-IQ1_S | 0.7 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/FluentlyQwen3-Coder-1.7B-i1-GGUF/resolve/main/FluentlyQwen3-Coder-1.7B.i1-IQ1_M.gguf) | i1-IQ1_M | 0.7 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/FluentlyQwen3-Coder-1.7B-i1-GGUF/resolve/main/FluentlyQwen3-Coder-1.7B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/FluentlyQwen3-Coder-1.7B-i1-GGUF/resolve/main/FluentlyQwen3-Coder-1.7B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/FluentlyQwen3-Coder-1.7B-i1-GGUF/resolve/main/FluentlyQwen3-Coder-1.7B.i1-IQ2_S.gguf) | i1-IQ2_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/FluentlyQwen3-Coder-1.7B-i1-GGUF/resolve/main/FluentlyQwen3-Coder-1.7B.i1-IQ2_M.gguf) | i1-IQ2_M | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/FluentlyQwen3-Coder-1.7B-i1-GGUF/resolve/main/FluentlyQwen3-Coder-1.7B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 0.9 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/FluentlyQwen3-Coder-1.7B-i1-GGUF/resolve/main/FluentlyQwen3-Coder-1.7B.i1-Q2_K.gguf) | i1-Q2_K | 1.0 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/FluentlyQwen3-Coder-1.7B-i1-GGUF/resolve/main/FluentlyQwen3-Coder-1.7B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/FluentlyQwen3-Coder-1.7B-i1-GGUF/resolve/main/FluentlyQwen3-Coder-1.7B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/FluentlyQwen3-Coder-1.7B-i1-GGUF/resolve/main/FluentlyQwen3-Coder-1.7B.i1-IQ3_S.gguf) | i1-IQ3_S | 1.1 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/FluentlyQwen3-Coder-1.7B-i1-GGUF/resolve/main/FluentlyQwen3-Coder-1.7B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 1.1 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/FluentlyQwen3-Coder-1.7B-i1-GGUF/resolve/main/FluentlyQwen3-Coder-1.7B.i1-IQ3_M.gguf) | i1-IQ3_M | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/FluentlyQwen3-Coder-1.7B-i1-GGUF/resolve/main/FluentlyQwen3-Coder-1.7B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 1.2 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/FluentlyQwen3-Coder-1.7B-i1-GGUF/resolve/main/FluentlyQwen3-Coder-1.7B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 1.2 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/FluentlyQwen3-Coder-1.7B-i1-GGUF/resolve/main/FluentlyQwen3-Coder-1.7B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/FluentlyQwen3-Coder-1.7B-i1-GGUF/resolve/main/FluentlyQwen3-Coder-1.7B.i1-IQ4_NL.gguf) | i1-IQ4_NL | 1.3 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/FluentlyQwen3-Coder-1.7B-i1-GGUF/resolve/main/FluentlyQwen3-Coder-1.7B.i1-Q4_0.gguf) | i1-Q4_0 | 1.3 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/FluentlyQwen3-Coder-1.7B-i1-GGUF/resolve/main/FluentlyQwen3-Coder-1.7B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 1.3 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/FluentlyQwen3-Coder-1.7B-i1-GGUF/resolve/main/FluentlyQwen3-Coder-1.7B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 1.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/FluentlyQwen3-Coder-1.7B-i1-GGUF/resolve/main/FluentlyQwen3-Coder-1.7B.i1-Q4_1.gguf) | i1-Q4_1 | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/FluentlyQwen3-Coder-1.7B-i1-GGUF/resolve/main/FluentlyQwen3-Coder-1.7B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/FluentlyQwen3-Coder-1.7B-i1-GGUF/resolve/main/FluentlyQwen3-Coder-1.7B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/FluentlyQwen3-Coder-1.7B-i1-GGUF/resolve/main/FluentlyQwen3-Coder-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. + +