commit 5765eb60237b35f279ad5990666907785227a2da Author: ModelHub XC Date: Fri Jul 17 10:42:07 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2.5-3B-Instruct-Reticent-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2b0c69c --- /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 +Qwen2.5-3B-Instruct-Reticent.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-Reticent.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-Reticent.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-Reticent.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-Reticent.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-Reticent.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-Reticent.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-Reticent.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-Reticent.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-Reticent.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-Reticent.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-Reticent.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-Reticent.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-Reticent.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-Reticent.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-Reticent.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-Reticent.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-Reticent.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-Reticent.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-Reticent.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-Reticent.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-Reticent.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-Reticent.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-Reticent.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-Reticent.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-3B-Instruct-Reticent.i1-IQ1_M.gguf b/Qwen2.5-3B-Instruct-Reticent.i1-IQ1_M.gguf new file mode 100644 index 0000000..83379c5 --- /dev/null +++ b/Qwen2.5-3B-Instruct-Reticent.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50dd2d1bf17972db578b63a71bc628cdb470a3bfc1d49573cb854dfd74c21a9b +size 850028384 diff --git a/Qwen2.5-3B-Instruct-Reticent.i1-IQ1_S.gguf b/Qwen2.5-3B-Instruct-Reticent.i1-IQ1_S.gguf new file mode 100644 index 0000000..faa35ed --- /dev/null +++ b/Qwen2.5-3B-Instruct-Reticent.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61f86ec00501008166ac34d48fdeca773bc0882b3a2ae9771a6ea44549e62e91 +size 791095136 diff --git a/Qwen2.5-3B-Instruct-Reticent.i1-IQ2_M.gguf b/Qwen2.5-3B-Instruct-Reticent.i1-IQ2_M.gguf new file mode 100644 index 0000000..ee05dd1 --- /dev/null +++ b/Qwen2.5-3B-Instruct-Reticent.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ded9d39e4f065bad63f8e413901a673c818e6ec7ff06f9c4a75750c1c4be9da5 +size 1140516704 diff --git a/Qwen2.5-3B-Instruct-Reticent.i1-IQ2_S.gguf b/Qwen2.5-3B-Instruct-Reticent.i1-IQ2_S.gguf new file mode 100644 index 0000000..c95ead6 --- /dev/null +++ b/Qwen2.5-3B-Instruct-Reticent.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da635132cb124412253b34be24064793d68b91f20affaf4ae8ab389a476857c4 +size 1061939040 diff --git a/Qwen2.5-3B-Instruct-Reticent.i1-IQ2_XS.gguf b/Qwen2.5-3B-Instruct-Reticent.i1-IQ2_XS.gguf new file mode 100644 index 0000000..a401db3 --- /dev/null +++ b/Qwen2.5-3B-Instruct-Reticent.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d59e87b52dd6b5232f5634c16c05e21f248ffe2ab09a1d3c82566c6404e8f78a +size 1031546720 diff --git a/Qwen2.5-3B-Instruct-Reticent.i1-IQ2_XXS.gguf b/Qwen2.5-3B-Instruct-Reticent.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..8b3541d --- /dev/null +++ b/Qwen2.5-3B-Instruct-Reticent.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48a7b2b14c74e3482fc08f8f77584ca5994b9b61b6c2e25b744e1c5104433c1d +size 948250464 diff --git a/Qwen2.5-3B-Instruct-Reticent.i1-IQ3_M.gguf b/Qwen2.5-3B-Instruct-Reticent.i1-IQ3_M.gguf new file mode 100644 index 0000000..276d533 --- /dev/null +++ b/Qwen2.5-3B-Instruct-Reticent.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da72a9bb0258bcc4c7cae209efba89a10ef3a159018cdaf8869196f6d13cfbd5 +size 1488895840 diff --git a/Qwen2.5-3B-Instruct-Reticent.i1-IQ3_S.gguf b/Qwen2.5-3B-Instruct-Reticent.i1-IQ3_S.gguf new file mode 100644 index 0000000..056c7e9 --- /dev/null +++ b/Qwen2.5-3B-Instruct-Reticent.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03df569866eba05e3f93cc1faffda5bb567c8baf6da4e9ef53d72cae8c93d785 +size 1456865120 diff --git a/Qwen2.5-3B-Instruct-Reticent.i1-IQ3_XS.gguf b/Qwen2.5-3B-Instruct-Reticent.i1-IQ3_XS.gguf new file mode 100644 index 0000000..5b3a31a --- /dev/null +++ b/Qwen2.5-3B-Instruct-Reticent.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef96537a589529dc846db30153fc449409ab00d7a3c00601287daf8e4a1d8d84 +size 1391837024 diff --git a/Qwen2.5-3B-Instruct-Reticent.i1-IQ3_XXS.gguf b/Qwen2.5-3B-Instruct-Reticent.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..2dcd871 --- /dev/null +++ b/Qwen2.5-3B-Instruct-Reticent.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c4941d0bc3ac073fc5014ea9112fbd8875a3c06a8d3529b9183f90df68254a6 +size 1282828128 diff --git a/Qwen2.5-3B-Instruct-Reticent.i1-IQ4_NL.gguf b/Qwen2.5-3B-Instruct-Reticent.i1-IQ4_NL.gguf new file mode 100644 index 0000000..c388ca6 --- /dev/null +++ b/Qwen2.5-3B-Instruct-Reticent.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6b71b93e97f8e4903036d4d4257fcd600fa084bc687fa67f453d49c9bfec80d +size 1825210208 diff --git a/Qwen2.5-3B-Instruct-Reticent.i1-IQ4_XS.gguf b/Qwen2.5-3B-Instruct-Reticent.i1-IQ4_XS.gguf new file mode 100644 index 0000000..caaeb11 --- /dev/null +++ b/Qwen2.5-3B-Instruct-Reticent.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fbe13298099f4868d10551b31658ef3fa58895376942152c61c8396640b86031 +size 1739095904 diff --git a/Qwen2.5-3B-Instruct-Reticent.i1-Q2_K.gguf b/Qwen2.5-3B-Instruct-Reticent.i1-Q2_K.gguf new file mode 100644 index 0000000..f19adec --- /dev/null +++ b/Qwen2.5-3B-Instruct-Reticent.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e31d5cad1d00d990d64b3b5c3693c98126bbe673f5ab6e129edecb0a7c3ddad +size 1274756960 diff --git a/Qwen2.5-3B-Instruct-Reticent.i1-Q2_K_S.gguf b/Qwen2.5-3B-Instruct-Reticent.i1-Q2_K_S.gguf new file mode 100644 index 0000000..e29ccf8 --- /dev/null +++ b/Qwen2.5-3B-Instruct-Reticent.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7af447faa2eac9baf99ddc74c4e8b16b5f7f27790c282bc63641b9376ad96d6d +size 1198128992 diff --git a/Qwen2.5-3B-Instruct-Reticent.i1-Q3_K_L.gguf b/Qwen2.5-3B-Instruct-Reticent.i1-Q3_K_L.gguf new file mode 100644 index 0000000..cb6ca83 --- /dev/null +++ b/Qwen2.5-3B-Instruct-Reticent.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc434eed12157c410ddc518667bf1ebea6eb4bca773a299cb2e7e14e1e5b5a34 +size 1707392864 diff --git a/Qwen2.5-3B-Instruct-Reticent.i1-Q3_K_M.gguf b/Qwen2.5-3B-Instruct-Reticent.i1-Q3_K_M.gguf new file mode 100644 index 0000000..c814551 --- /dev/null +++ b/Qwen2.5-3B-Instruct-Reticent.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81fe636f9f32ea0dcb5cad21870b6e189b4b1879e615618bb6f7290542719a5f +size 1590476640 diff --git a/Qwen2.5-3B-Instruct-Reticent.i1-Q3_K_S.gguf b/Qwen2.5-3B-Instruct-Reticent.i1-Q3_K_S.gguf new file mode 100644 index 0000000..64ea47d --- /dev/null +++ b/Qwen2.5-3B-Instruct-Reticent.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f91826aecfde7e7eb2f62fd4f5d1bdab375c53985409ada1f7487c2270166a1 +size 1454358368 diff --git a/Qwen2.5-3B-Instruct-Reticent.i1-Q4_0.gguf b/Qwen2.5-3B-Instruct-Reticent.i1-Q4_0.gguf new file mode 100644 index 0000000..a307d8c --- /dev/null +++ b/Qwen2.5-3B-Instruct-Reticent.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7aa4bf1402d3e9aaeb65cd4e17232bf858b8dcdf94431968f0ed59fed5245770 +size 1828487008 diff --git a/Qwen2.5-3B-Instruct-Reticent.i1-Q4_1.gguf b/Qwen2.5-3B-Instruct-Reticent.i1-Q4_1.gguf new file mode 100644 index 0000000..6732353 --- /dev/null +++ b/Qwen2.5-3B-Instruct-Reticent.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32afbc60b1440a61646be74b869b0fa93c4c8e828513a4bd552af5c1d8a19fe8 +size 1996259168 diff --git a/Qwen2.5-3B-Instruct-Reticent.i1-Q4_K_M.gguf b/Qwen2.5-3B-Instruct-Reticent.i1-Q4_K_M.gguf new file mode 100644 index 0000000..f7999fe --- /dev/null +++ b/Qwen2.5-3B-Instruct-Reticent.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f35b00ad7f72411aaffcf36480c15210b6246c2192f3b535fdcb95752fd5723 +size 1929903968 diff --git a/Qwen2.5-3B-Instruct-Reticent.i1-Q4_K_S.gguf b/Qwen2.5-3B-Instruct-Reticent.i1-Q4_K_S.gguf new file mode 100644 index 0000000..abadcd1 --- /dev/null +++ b/Qwen2.5-3B-Instruct-Reticent.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83b5a261928ce654b04e0e72ca5d278b80dae2cb2be958e6ce34bb6536d5357b +size 1834385248 diff --git a/Qwen2.5-3B-Instruct-Reticent.i1-Q5_K_M.gguf b/Qwen2.5-3B-Instruct-Reticent.i1-Q5_K_M.gguf new file mode 100644 index 0000000..6132799 --- /dev/null +++ b/Qwen2.5-3B-Instruct-Reticent.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d1b41a1c9b56f4393f2ad9e8afffb3a6499a55dbe5b23694b492599f3e64c22 +size 2224815968 diff --git a/Qwen2.5-3B-Instruct-Reticent.i1-Q5_K_S.gguf b/Qwen2.5-3B-Instruct-Reticent.i1-Q5_K_S.gguf new file mode 100644 index 0000000..52549f7 --- /dev/null +++ b/Qwen2.5-3B-Instruct-Reticent.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79fc114e18032bfe0a3c0037a4699db8f6b5eddda0063008d5e64c1f1451ba3d +size 2169667424 diff --git a/Qwen2.5-3B-Instruct-Reticent.i1-Q6_K.gguf b/Qwen2.5-3B-Instruct-Reticent.i1-Q6_K.gguf new file mode 100644 index 0000000..7147bab --- /dev/null +++ b/Qwen2.5-3B-Instruct-Reticent.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0e34e35a72397cb725e19cb3632e01355954d3eb52a75c965f8d31cb9e176fc +size 2538159968 diff --git a/Qwen2.5-3B-Instruct-Reticent.imatrix.gguf b/Qwen2.5-3B-Instruct-Reticent.imatrix.gguf new file mode 100644 index 0000000..ab132a3 --- /dev/null +++ b/Qwen2.5-3B-Instruct-Reticent.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10529dd71ee4b94478aa4b4814ce823424bc70b02880e2b0136e3cee5bce0e6b +size 3393408 diff --git a/README.md b/README.md new file mode 100644 index 0000000..68fe41c --- /dev/null +++ b/README.md @@ -0,0 +1,90 @@ +--- +base_model: Firworks/Qwen2.5-3B-Instruct-Reticent +datasets: +- Firworks/reticent-100k +language: +- en +library_name: transformers +license: wtfpl +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- fine-tuned +- reticent +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/Firworks/Qwen2.5-3B-Instruct-Reticent + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen2.5-3B-Instruct-Reticent-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Reticent-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/Qwen2.5-3B-Instruct-Reticent-i1-GGUF/resolve/main/Qwen2.5-3B-Instruct-Reticent.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Reticent-i1-GGUF/resolve/main/Qwen2.5-3B-Instruct-Reticent.i1-IQ1_S.gguf) | i1-IQ1_S | 0.9 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Reticent-i1-GGUF/resolve/main/Qwen2.5-3B-Instruct-Reticent.i1-IQ1_M.gguf) | i1-IQ1_M | 1.0 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Reticent-i1-GGUF/resolve/main/Qwen2.5-3B-Instruct-Reticent.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Reticent-i1-GGUF/resolve/main/Qwen2.5-3B-Instruct-Reticent.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Reticent-i1-GGUF/resolve/main/Qwen2.5-3B-Instruct-Reticent.i1-IQ2_S.gguf) | i1-IQ2_S | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Reticent-i1-GGUF/resolve/main/Qwen2.5-3B-Instruct-Reticent.i1-IQ2_M.gguf) | i1-IQ2_M | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Reticent-i1-GGUF/resolve/main/Qwen2.5-3B-Instruct-Reticent.i1-Q2_K_S.gguf) | i1-Q2_K_S | 1.3 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Reticent-i1-GGUF/resolve/main/Qwen2.5-3B-Instruct-Reticent.i1-Q2_K.gguf) | i1-Q2_K | 1.4 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Reticent-i1-GGUF/resolve/main/Qwen2.5-3B-Instruct-Reticent.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Reticent-i1-GGUF/resolve/main/Qwen2.5-3B-Instruct-Reticent.i1-IQ3_XS.gguf) | i1-IQ3_XS | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Reticent-i1-GGUF/resolve/main/Qwen2.5-3B-Instruct-Reticent.i1-Q3_K_S.gguf) | i1-Q3_K_S | 1.6 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Reticent-i1-GGUF/resolve/main/Qwen2.5-3B-Instruct-Reticent.i1-IQ3_S.gguf) | i1-IQ3_S | 1.6 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Reticent-i1-GGUF/resolve/main/Qwen2.5-3B-Instruct-Reticent.i1-IQ3_M.gguf) | i1-IQ3_M | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Reticent-i1-GGUF/resolve/main/Qwen2.5-3B-Instruct-Reticent.i1-Q3_K_M.gguf) | i1-Q3_K_M | 1.7 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Reticent-i1-GGUF/resolve/main/Qwen2.5-3B-Instruct-Reticent.i1-Q3_K_L.gguf) | i1-Q3_K_L | 1.8 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Reticent-i1-GGUF/resolve/main/Qwen2.5-3B-Instruct-Reticent.i1-IQ4_XS.gguf) | i1-IQ4_XS | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Reticent-i1-GGUF/resolve/main/Qwen2.5-3B-Instruct-Reticent.i1-IQ4_NL.gguf) | i1-IQ4_NL | 1.9 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Reticent-i1-GGUF/resolve/main/Qwen2.5-3B-Instruct-Reticent.i1-Q4_0.gguf) | i1-Q4_0 | 1.9 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Reticent-i1-GGUF/resolve/main/Qwen2.5-3B-Instruct-Reticent.i1-Q4_K_S.gguf) | i1-Q4_K_S | 1.9 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Reticent-i1-GGUF/resolve/main/Qwen2.5-3B-Instruct-Reticent.i1-Q4_K_M.gguf) | i1-Q4_K_M | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Reticent-i1-GGUF/resolve/main/Qwen2.5-3B-Instruct-Reticent.i1-Q4_1.gguf) | i1-Q4_1 | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Reticent-i1-GGUF/resolve/main/Qwen2.5-3B-Instruct-Reticent.i1-Q5_K_S.gguf) | i1-Q5_K_S | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Reticent-i1-GGUF/resolve/main/Qwen2.5-3B-Instruct-Reticent.i1-Q5_K_M.gguf) | i1-Q5_K_M | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Reticent-i1-GGUF/resolve/main/Qwen2.5-3B-Instruct-Reticent.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. + +