commit 6c7ccab70698577d9933b6ad8165f6dada44ea41 Author: ModelHub XC Date: Wed Jun 17 07:16:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/QwensanLoRA-3B-Merge-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..3f92c13 --- /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 +QwensanLoRA-3B-Merge.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +QwensanLoRA-3B-Merge.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +QwensanLoRA-3B-Merge.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +QwensanLoRA-3B-Merge.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +QwensanLoRA-3B-Merge.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +QwensanLoRA-3B-Merge.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +QwensanLoRA-3B-Merge.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +QwensanLoRA-3B-Merge.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +QwensanLoRA-3B-Merge.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +QwensanLoRA-3B-Merge.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +QwensanLoRA-3B-Merge.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +QwensanLoRA-3B-Merge.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +QwensanLoRA-3B-Merge.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +QwensanLoRA-3B-Merge.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +QwensanLoRA-3B-Merge.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +QwensanLoRA-3B-Merge.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +QwensanLoRA-3B-Merge.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +QwensanLoRA-3B-Merge.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +QwensanLoRA-3B-Merge.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +QwensanLoRA-3B-Merge.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +QwensanLoRA-3B-Merge.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +QwensanLoRA-3B-Merge.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +QwensanLoRA-3B-Merge.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +QwensanLoRA-3B-Merge.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +QwensanLoRA-3B-Merge.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/QwensanLoRA-3B-Merge.i1-IQ1_M.gguf b/QwensanLoRA-3B-Merge.i1-IQ1_M.gguf new file mode 100644 index 0000000..86830b1 --- /dev/null +++ b/QwensanLoRA-3B-Merge.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:325f16d77156dd836dfa055922837afe85e98779e404da40be506696c24e043a +size 850028640 diff --git a/QwensanLoRA-3B-Merge.i1-IQ1_S.gguf b/QwensanLoRA-3B-Merge.i1-IQ1_S.gguf new file mode 100644 index 0000000..88483c1 --- /dev/null +++ b/QwensanLoRA-3B-Merge.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0091fb3b5ec3d42a6083227711b55b9a401a38a4c1ac45c547f0921ed8040a8 +size 791095392 diff --git a/QwensanLoRA-3B-Merge.i1-IQ2_M.gguf b/QwensanLoRA-3B-Merge.i1-IQ2_M.gguf new file mode 100644 index 0000000..8e50920 --- /dev/null +++ b/QwensanLoRA-3B-Merge.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f95f6d21201a50a5172cb4cb9451610dc44d92e66de6eafe3d88d53d1ebd0681 +size 1140516960 diff --git a/QwensanLoRA-3B-Merge.i1-IQ2_S.gguf b/QwensanLoRA-3B-Merge.i1-IQ2_S.gguf new file mode 100644 index 0000000..c98ba61 --- /dev/null +++ b/QwensanLoRA-3B-Merge.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d6e29c53a1499a38cf8ce4f3b545dd4189b2597953e2c2eb94ddd533a3a7d46 +size 1061939296 diff --git a/QwensanLoRA-3B-Merge.i1-IQ2_XS.gguf b/QwensanLoRA-3B-Merge.i1-IQ2_XS.gguf new file mode 100644 index 0000000..c30a11b --- /dev/null +++ b/QwensanLoRA-3B-Merge.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:356feb8ebfcdb813f0444f83732d52bac988db915e197c1d8f36f91dc8d173b8 +size 1031546976 diff --git a/QwensanLoRA-3B-Merge.i1-IQ2_XXS.gguf b/QwensanLoRA-3B-Merge.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..5331e6b --- /dev/null +++ b/QwensanLoRA-3B-Merge.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6949a222a6db1ec6371547c39ab9a28a4a79b1e8be235636de4c472339dc099c +size 948250720 diff --git a/QwensanLoRA-3B-Merge.i1-IQ3_M.gguf b/QwensanLoRA-3B-Merge.i1-IQ3_M.gguf new file mode 100644 index 0000000..ad45774 --- /dev/null +++ b/QwensanLoRA-3B-Merge.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6c1039f7657809e26fd289551a768fbedda712600cfe76a9dc4bce79afc351f +size 1488896096 diff --git a/QwensanLoRA-3B-Merge.i1-IQ3_S.gguf b/QwensanLoRA-3B-Merge.i1-IQ3_S.gguf new file mode 100644 index 0000000..d59a850 --- /dev/null +++ b/QwensanLoRA-3B-Merge.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:264e9449b03749a494baac73b772713554882745cbde29e4a6fad6dfc93875d4 +size 1456865376 diff --git a/QwensanLoRA-3B-Merge.i1-IQ3_XS.gguf b/QwensanLoRA-3B-Merge.i1-IQ3_XS.gguf new file mode 100644 index 0000000..aa62627 --- /dev/null +++ b/QwensanLoRA-3B-Merge.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:863b736067aec22f796c7ddd3ab0a30df918559899df3f72865428a994f593a6 +size 1391837280 diff --git a/QwensanLoRA-3B-Merge.i1-IQ3_XXS.gguf b/QwensanLoRA-3B-Merge.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..b89f374 --- /dev/null +++ b/QwensanLoRA-3B-Merge.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c194809f376842dad144149d56ac81250654df2bc2ad8b04b9065f5e2a3ba6ca +size 1282828384 diff --git a/QwensanLoRA-3B-Merge.i1-IQ4_NL.gguf b/QwensanLoRA-3B-Merge.i1-IQ4_NL.gguf new file mode 100644 index 0000000..fc494a7 --- /dev/null +++ b/QwensanLoRA-3B-Merge.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d57381a5492397801f85350bc69d31c3a8d68d910606729b9044ad443ce4a2c8 +size 1825210464 diff --git a/QwensanLoRA-3B-Merge.i1-IQ4_XS.gguf b/QwensanLoRA-3B-Merge.i1-IQ4_XS.gguf new file mode 100644 index 0000000..39a093a --- /dev/null +++ b/QwensanLoRA-3B-Merge.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd12f16b01a3b93e7efa2ea481a573ccd7d237ca08ec88316bd00d7b353f74c0 +size 1739096160 diff --git a/QwensanLoRA-3B-Merge.i1-Q2_K.gguf b/QwensanLoRA-3B-Merge.i1-Q2_K.gguf new file mode 100644 index 0000000..66ea730 --- /dev/null +++ b/QwensanLoRA-3B-Merge.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4c89775df1b6ba7d08842e46f5c123a579bddfb2425f4eb67575e4e7d5ddd97 +size 1274757216 diff --git a/QwensanLoRA-3B-Merge.i1-Q2_K_S.gguf b/QwensanLoRA-3B-Merge.i1-Q2_K_S.gguf new file mode 100644 index 0000000..170f474 --- /dev/null +++ b/QwensanLoRA-3B-Merge.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07bc356467e0ae13ff049ae2c8583ac81b8f15dd2c49742a56ee2072b7cb983e +size 1198129248 diff --git a/QwensanLoRA-3B-Merge.i1-Q3_K_L.gguf b/QwensanLoRA-3B-Merge.i1-Q3_K_L.gguf new file mode 100644 index 0000000..a28bccc --- /dev/null +++ b/QwensanLoRA-3B-Merge.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d7dc79872e29d71ba90d108956206e6bfc9938bb4483e6578bbafd00f73f8ea +size 1707393120 diff --git a/QwensanLoRA-3B-Merge.i1-Q3_K_M.gguf b/QwensanLoRA-3B-Merge.i1-Q3_K_M.gguf new file mode 100644 index 0000000..95b2605 --- /dev/null +++ b/QwensanLoRA-3B-Merge.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1218eb73341782d2ccd60d51090c09df7aa490f9d902c5879f0f6a0be2da16b3 +size 1590476896 diff --git a/QwensanLoRA-3B-Merge.i1-Q3_K_S.gguf b/QwensanLoRA-3B-Merge.i1-Q3_K_S.gguf new file mode 100644 index 0000000..9d8540a --- /dev/null +++ b/QwensanLoRA-3B-Merge.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:216df6db11cb7317e12c8d6a6ec613a580d96eec97c83404c1917e513fb950e2 +size 1454358624 diff --git a/QwensanLoRA-3B-Merge.i1-Q4_0.gguf b/QwensanLoRA-3B-Merge.i1-Q4_0.gguf new file mode 100644 index 0000000..8682e47 --- /dev/null +++ b/QwensanLoRA-3B-Merge.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7bc812243a787dff49f8cae2db209df8515dcec817d7b24c84628a62fda2288 +size 1828487264 diff --git a/QwensanLoRA-3B-Merge.i1-Q4_1.gguf b/QwensanLoRA-3B-Merge.i1-Q4_1.gguf new file mode 100644 index 0000000..e41a64c --- /dev/null +++ b/QwensanLoRA-3B-Merge.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2aecc8aa6e2c50088b3a329f2674de1e3b8d39579e293fdb34de5528f1d4334b +size 1996259424 diff --git a/QwensanLoRA-3B-Merge.i1-Q4_K_M.gguf b/QwensanLoRA-3B-Merge.i1-Q4_K_M.gguf new file mode 100644 index 0000000..a768005 --- /dev/null +++ b/QwensanLoRA-3B-Merge.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a592ccd83d0932c2d114e746ea3c1670ce4e0a383cfc89e278cba4c988852300 +size 1929904224 diff --git a/QwensanLoRA-3B-Merge.i1-Q4_K_S.gguf b/QwensanLoRA-3B-Merge.i1-Q4_K_S.gguf new file mode 100644 index 0000000..ba7afcf --- /dev/null +++ b/QwensanLoRA-3B-Merge.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a22ab537966ca4d7146e94e4853ba2d81ce5bf2d08fc66cac96b1fb73317174 +size 1834385504 diff --git a/QwensanLoRA-3B-Merge.i1-Q5_K_M.gguf b/QwensanLoRA-3B-Merge.i1-Q5_K_M.gguf new file mode 100644 index 0000000..03b9a80 --- /dev/null +++ b/QwensanLoRA-3B-Merge.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:945c257cca11086a39da7642e6af91a5efa9c06932171a8869af420cb4e30730 +size 2224816224 diff --git a/QwensanLoRA-3B-Merge.i1-Q5_K_S.gguf b/QwensanLoRA-3B-Merge.i1-Q5_K_S.gguf new file mode 100644 index 0000000..b8bdbea --- /dev/null +++ b/QwensanLoRA-3B-Merge.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3da30abf13e6ebd4f68b02c584b48b596112dafda8e53a0f9cfb70b4c67946ed +size 2169667680 diff --git a/QwensanLoRA-3B-Merge.i1-Q6_K.gguf b/QwensanLoRA-3B-Merge.i1-Q6_K.gguf new file mode 100644 index 0000000..9880661 --- /dev/null +++ b/QwensanLoRA-3B-Merge.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26b52a6c6ba0a75a4f98c615990fe3e76aa6428e5f03b9706963526e3795bfb1 +size 2538160224 diff --git a/QwensanLoRA-3B-Merge.imatrix.gguf b/QwensanLoRA-3B-Merge.imatrix.gguf new file mode 100644 index 0000000..00ab00c --- /dev/null +++ b/QwensanLoRA-3B-Merge.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8125a726a4305f388e97f4636a7ce076eba56be80c8f8bd5636a1da77856a85c +size 3393408 diff --git a/README.md b/README.md new file mode 100644 index 0000000..1a18f32 --- /dev/null +++ b/README.md @@ -0,0 +1,94 @@ +--- +base_model: XzyanQi/QwensanLoRA-3B-Merge +datasets: +- Amod/mental_health_counseling_conversations +- ShenLab/MentalChat16K +language: +- id +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- mental-health +- counseling +- indonesia +- qwen +- lora +- qlora +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/XzyanQi/QwensanLoRA-3B-Merge + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#QwensanLoRA-3B-Merge-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/QwensanLoRA-3B-Merge-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/QwensanLoRA-3B-Merge-i1-GGUF/resolve/main/QwensanLoRA-3B-Merge.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/QwensanLoRA-3B-Merge-i1-GGUF/resolve/main/QwensanLoRA-3B-Merge.i1-IQ1_S.gguf) | i1-IQ1_S | 0.9 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/QwensanLoRA-3B-Merge-i1-GGUF/resolve/main/QwensanLoRA-3B-Merge.i1-IQ1_M.gguf) | i1-IQ1_M | 1.0 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/QwensanLoRA-3B-Merge-i1-GGUF/resolve/main/QwensanLoRA-3B-Merge.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/QwensanLoRA-3B-Merge-i1-GGUF/resolve/main/QwensanLoRA-3B-Merge.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/QwensanLoRA-3B-Merge-i1-GGUF/resolve/main/QwensanLoRA-3B-Merge.i1-IQ2_S.gguf) | i1-IQ2_S | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/QwensanLoRA-3B-Merge-i1-GGUF/resolve/main/QwensanLoRA-3B-Merge.i1-IQ2_M.gguf) | i1-IQ2_M | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/QwensanLoRA-3B-Merge-i1-GGUF/resolve/main/QwensanLoRA-3B-Merge.i1-Q2_K_S.gguf) | i1-Q2_K_S | 1.3 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/QwensanLoRA-3B-Merge-i1-GGUF/resolve/main/QwensanLoRA-3B-Merge.i1-Q2_K.gguf) | i1-Q2_K | 1.4 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/QwensanLoRA-3B-Merge-i1-GGUF/resolve/main/QwensanLoRA-3B-Merge.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/QwensanLoRA-3B-Merge-i1-GGUF/resolve/main/QwensanLoRA-3B-Merge.i1-IQ3_XS.gguf) | i1-IQ3_XS | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/QwensanLoRA-3B-Merge-i1-GGUF/resolve/main/QwensanLoRA-3B-Merge.i1-Q3_K_S.gguf) | i1-Q3_K_S | 1.6 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/QwensanLoRA-3B-Merge-i1-GGUF/resolve/main/QwensanLoRA-3B-Merge.i1-IQ3_S.gguf) | i1-IQ3_S | 1.6 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/QwensanLoRA-3B-Merge-i1-GGUF/resolve/main/QwensanLoRA-3B-Merge.i1-IQ3_M.gguf) | i1-IQ3_M | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/QwensanLoRA-3B-Merge-i1-GGUF/resolve/main/QwensanLoRA-3B-Merge.i1-Q3_K_M.gguf) | i1-Q3_K_M | 1.7 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/QwensanLoRA-3B-Merge-i1-GGUF/resolve/main/QwensanLoRA-3B-Merge.i1-Q3_K_L.gguf) | i1-Q3_K_L | 1.8 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/QwensanLoRA-3B-Merge-i1-GGUF/resolve/main/QwensanLoRA-3B-Merge.i1-IQ4_XS.gguf) | i1-IQ4_XS | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/QwensanLoRA-3B-Merge-i1-GGUF/resolve/main/QwensanLoRA-3B-Merge.i1-IQ4_NL.gguf) | i1-IQ4_NL | 1.9 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/QwensanLoRA-3B-Merge-i1-GGUF/resolve/main/QwensanLoRA-3B-Merge.i1-Q4_0.gguf) | i1-Q4_0 | 1.9 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/QwensanLoRA-3B-Merge-i1-GGUF/resolve/main/QwensanLoRA-3B-Merge.i1-Q4_K_S.gguf) | i1-Q4_K_S | 1.9 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/QwensanLoRA-3B-Merge-i1-GGUF/resolve/main/QwensanLoRA-3B-Merge.i1-Q4_K_M.gguf) | i1-Q4_K_M | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/QwensanLoRA-3B-Merge-i1-GGUF/resolve/main/QwensanLoRA-3B-Merge.i1-Q4_1.gguf) | i1-Q4_1 | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/QwensanLoRA-3B-Merge-i1-GGUF/resolve/main/QwensanLoRA-3B-Merge.i1-Q5_K_S.gguf) | i1-Q5_K_S | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/QwensanLoRA-3B-Merge-i1-GGUF/resolve/main/QwensanLoRA-3B-Merge.i1-Q5_K_M.gguf) | i1-Q5_K_M | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/QwensanLoRA-3B-Merge-i1-GGUF/resolve/main/QwensanLoRA-3B-Merge.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. + +