commit a2eddaec8dfc9bb98d4d9addfec6d68e45bf8f72 Author: ModelHub XC Date: Wed May 27 09:11:16 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-4B-Element18-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..9cfc7c9 --- /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 +Qwen3-4B-Element18.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Element18.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Element18.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Element18.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Element18.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Element18.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Element18.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Element18.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Element18.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Element18.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Element18.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Element18.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Element18.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Element18.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Element18.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Element18.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Element18.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Element18.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Element18.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Element18.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Element18.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Element18.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Element18.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Element18.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Element18.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-4B-Element18.i1-IQ1_M.gguf b/Qwen3-4B-Element18.i1-IQ1_M.gguf new file mode 100644 index 0000000..0227334 --- /dev/null +++ b/Qwen3-4B-Element18.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3f93a8e277188114d1a083a812befbd217d3f82ffba5dc98a831d85d674878c +size 1127026304 diff --git a/Qwen3-4B-Element18.i1-IQ1_S.gguf b/Qwen3-4B-Element18.i1-IQ1_S.gguf new file mode 100644 index 0000000..f989e7a --- /dev/null +++ b/Qwen3-4B-Element18.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57e5ea41267790a3623dd08274588189530455e24248c4ea57caf7a829e8b82a +size 1055264384 diff --git a/Qwen3-4B-Element18.i1-IQ2_M.gguf b/Qwen3-4B-Element18.i1-IQ2_M.gguf new file mode 100644 index 0000000..5f8f71d --- /dev/null +++ b/Qwen3-4B-Element18.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7036698838a3093c8161ef9c790e28e7e0804a297ce078205d12023cd2a59c7b +size 1512992384 diff --git a/Qwen3-4B-Element18.i1-IQ2_S.gguf b/Qwen3-4B-Element18.i1-IQ2_S.gguf new file mode 100644 index 0000000..51d2269 --- /dev/null +++ b/Qwen3-4B-Element18.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5c8bcaf0c8348facce1f8515637c73d7af58221342c97793c0cb87daca6cdca +size 1417309824 diff --git a/Qwen3-4B-Element18.i1-IQ2_XS.gguf b/Qwen3-4B-Element18.i1-IQ2_XS.gguf new file mode 100644 index 0000000..9ddb7bb --- /dev/null +++ b/Qwen3-4B-Element18.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d3031bd47fafb8a05ac03205f57859822c1015a6fb76b0c698341211e3ac1a1 +size 1354108544 diff --git a/Qwen3-4B-Element18.i1-IQ2_XXS.gguf b/Qwen3-4B-Element18.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..33eeb60 --- /dev/null +++ b/Qwen3-4B-Element18.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8bc94d2ff5840385eebf00e149474be5faa8bfd7993ea4544f3e4d1af4918c61 +size 1246629504 diff --git a/Qwen3-4B-Element18.i1-IQ3_M.gguf b/Qwen3-4B-Element18.i1-IQ3_M.gguf new file mode 100644 index 0000000..05a05fe --- /dev/null +++ b/Qwen3-4B-Element18.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08624a6c40a3a61194a3e49d54ea6c0b90f03e47b5ed7255592d76efdc158ba8 +size 1962904704 diff --git a/Qwen3-4B-Element18.i1-IQ3_S.gguf b/Qwen3-4B-Element18.i1-IQ3_S.gguf new file mode 100644 index 0000000..7c0a849 --- /dev/null +++ b/Qwen3-4B-Element18.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9353e2eb61c56eb1fd26cc2da0cff46427d5d9cd9591c0d73ed69ba08df07a9 +size 1899539584 diff --git a/Qwen3-4B-Element18.i1-IQ3_XS.gguf b/Qwen3-4B-Element18.i1-IQ3_XS.gguf new file mode 100644 index 0000000..4039f19 --- /dev/null +++ b/Qwen3-4B-Element18.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:114d58aabe5302e7c9c587146bfe115f2017d3cb8d7d5912f7c69685457b9aef +size 1814383744 diff --git a/Qwen3-4B-Element18.i1-IQ3_XXS.gguf b/Qwen3-4B-Element18.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..7845ef0 --- /dev/null +++ b/Qwen3-4B-Element18.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07d64da4cf2f6528d5d0348c489f9e23230b6f46eb6c98d5e6dc9795181cd124 +size 1670196864 diff --git a/Qwen3-4B-Element18.i1-IQ4_NL.gguf b/Qwen3-4B-Element18.i1-IQ4_NL.gguf new file mode 100644 index 0000000..cf93ddb --- /dev/null +++ b/Qwen3-4B-Element18.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc60d15a12ffae84a3d3b5a610814514060f2dd50eba7afb165ba0a7841af147 +size 2381352064 diff --git a/Qwen3-4B-Element18.i1-IQ4_XS.gguf b/Qwen3-4B-Element18.i1-IQ4_XS.gguf new file mode 100644 index 0000000..3aff61c --- /dev/null +++ b/Qwen3-4B-Element18.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:976609e10fb76164aff697037fac863835abec116a7d79bb744dd4ce04530c03 +size 2270760064 diff --git a/Qwen3-4B-Element18.i1-Q2_K.gguf b/Qwen3-4B-Element18.i1-Q2_K.gguf new file mode 100644 index 0000000..d16f2ce --- /dev/null +++ b/Qwen3-4B-Element18.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8cef18593b157b4bdf95ecd1314094999ad0972fbbbbe0d8ed3f0e32b275c415 +size 1669508224 diff --git a/Qwen3-4B-Element18.i1-Q2_K_S.gguf b/Qwen3-4B-Element18.i1-Q2_K_S.gguf new file mode 100644 index 0000000..0724f20 --- /dev/null +++ b/Qwen3-4B-Element18.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:189bfa88e2d6944f0f48c29c15e4c69f8c8dc8d5f305522831822228ab6a8275 +size 1563462784 diff --git a/Qwen3-4B-Element18.i1-Q3_K_L.gguf b/Qwen3-4B-Element18.i1-Q3_K_L.gguf new file mode 100644 index 0000000..e4bd3ad --- /dev/null +++ b/Qwen3-4B-Element18.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e32aff2727d66e3bf02f429f1fcbbb22ff71e397d7ab02acce36ff06a3fb22e +size 2239794304 diff --git a/Qwen3-4B-Element18.i1-Q3_K_M.gguf b/Qwen3-4B-Element18.i1-Q3_K_M.gguf new file mode 100644 index 0000000..e39c699 --- /dev/null +++ b/Qwen3-4B-Element18.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88c1fd120fa0e017135fb7140bee7d04e937c9ab660cbc13683fc4aa369be350 +size 2075626624 diff --git a/Qwen3-4B-Element18.i1-Q3_K_S.gguf b/Qwen3-4B-Element18.i1-Q3_K_S.gguf new file mode 100644 index 0000000..ba52702 --- /dev/null +++ b/Qwen3-4B-Element18.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e91bbfb35df2933a04bf72e87234f638ce3874c2b1e3e8b6b42455bda5f0e625 +size 1887005824 diff --git a/Qwen3-4B-Element18.i1-Q4_0.gguf b/Qwen3-4B-Element18.i1-Q4_0.gguf new file mode 100644 index 0000000..c556c31 --- /dev/null +++ b/Qwen3-4B-Element18.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13fc1a8a9f41a76c612a139fd948cbefe0938f3acc2dffd2272c80525c7accbc +size 2375781504 diff --git a/Qwen3-4B-Element18.i1-Q4_1.gguf b/Qwen3-4B-Element18.i1-Q4_1.gguf new file mode 100644 index 0000000..9bcead1 --- /dev/null +++ b/Qwen3-4B-Element18.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46c993b65c7273bfba6ba04d00c3daa620b1c6d9c08256b6cbe7af3f201e990b +size 2596637824 diff --git a/Qwen3-4B-Element18.i1-Q4_K_M.gguf b/Qwen3-4B-Element18.i1-Q4_K_M.gguf new file mode 100644 index 0000000..8115338 --- /dev/null +++ b/Qwen3-4B-Element18.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00df36cee6c99a48f47f6d14900d9e70b5fbba226d987558000139f0dd0e314f +size 2497289344 diff --git a/Qwen3-4B-Element18.i1-Q4_K_S.gguf b/Qwen3-4B-Element18.i1-Q4_K_S.gguf new file mode 100644 index 0000000..c1ecc0c --- /dev/null +++ b/Qwen3-4B-Element18.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc7e41fae15457c5624db2930d905687d33adcd8551e53e8f354755b7f8e1e36 +size 2383318144 diff --git a/Qwen3-4B-Element18.i1-Q5_K_M.gguf b/Qwen3-4B-Element18.i1-Q5_K_M.gguf new file mode 100644 index 0000000..62aa2c3 --- /dev/null +++ b/Qwen3-4B-Element18.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:603bd0761908a765b438e99561dcac3c4bdb5e129aae5024823ea04998d4de2e +size 2889522304 diff --git a/Qwen3-4B-Element18.i1-Q5_K_S.gguf b/Qwen3-4B-Element18.i1-Q5_K_S.gguf new file mode 100644 index 0000000..b4cff95 --- /dev/null +++ b/Qwen3-4B-Element18.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfefa6d6e783ffb905fdc89bd05132cb55ba55fbaa5bf5a18597a4ce5188d9e7 +size 2823720064 diff --git a/Qwen3-4B-Element18.i1-Q6_K.gguf b/Qwen3-4B-Element18.i1-Q6_K.gguf new file mode 100644 index 0000000..7b44cd2 --- /dev/null +++ b/Qwen3-4B-Element18.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6a9433807d4ffca8c9a6523670eb5a2e8dea0327a12ebe751c8467ed609fbc3 +size 3306269824 diff --git a/Qwen3-4B-Element18.imatrix.gguf b/Qwen3-4B-Element18.imatrix.gguf new file mode 100644 index 0000000..7020784 --- /dev/null +++ b/Qwen3-4B-Element18.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1f0556418ea557d81624c94c004b537da56815a801fdb9604bc09cea373bf7a +size 3872640 diff --git a/README.md b/README.md new file mode 100644 index 0000000..694a6a5 --- /dev/null +++ b/README.md @@ -0,0 +1,116 @@ +--- +base_model: nightmedia/Qwen3-4B-Element18 +language: +- en +- zh +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- coding +- research +- deep thinking +- 1M context +- 256k context +- Qwen3 +- All use cases +- creative +- creative writing +- fiction writing +- plot generation +- sub-plot generation +- story generation +- scene continue +- storytelling +- fiction story +- science fiction +- all genres +- story +- writing +- vivid prosing +- vivid writing +- fiction +- roleplaying +- bfloat16 +- finetune +- mergekit +- merge +- mlx +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/nightmedia/Qwen3-4B-Element18 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-4B-Element18-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Qwen3-4B-Element18-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/Qwen3-4B-Element18-i1-GGUF/resolve/main/Qwen3-4B-Element18.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Element18-i1-GGUF/resolve/main/Qwen3-4B-Element18.i1-IQ1_S.gguf) | i1-IQ1_S | 1.2 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Element18-i1-GGUF/resolve/main/Qwen3-4B-Element18.i1-IQ1_M.gguf) | i1-IQ1_M | 1.2 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Element18-i1-GGUF/resolve/main/Qwen3-4B-Element18.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Element18-i1-GGUF/resolve/main/Qwen3-4B-Element18.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Element18-i1-GGUF/resolve/main/Qwen3-4B-Element18.i1-IQ2_S.gguf) | i1-IQ2_S | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Element18-i1-GGUF/resolve/main/Qwen3-4B-Element18.i1-IQ2_M.gguf) | i1-IQ2_M | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Element18-i1-GGUF/resolve/main/Qwen3-4B-Element18.i1-Q2_K_S.gguf) | i1-Q2_K_S | 1.7 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Element18-i1-GGUF/resolve/main/Qwen3-4B-Element18.i1-Q2_K.gguf) | i1-Q2_K | 1.8 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Element18-i1-GGUF/resolve/main/Qwen3-4B-Element18.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Element18-i1-GGUF/resolve/main/Qwen3-4B-Element18.i1-IQ3_XS.gguf) | i1-IQ3_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Element18-i1-GGUF/resolve/main/Qwen3-4B-Element18.i1-Q3_K_S.gguf) | i1-Q3_K_S | 2.0 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Element18-i1-GGUF/resolve/main/Qwen3-4B-Element18.i1-IQ3_S.gguf) | i1-IQ3_S | 2.0 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Element18-i1-GGUF/resolve/main/Qwen3-4B-Element18.i1-IQ3_M.gguf) | i1-IQ3_M | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Element18-i1-GGUF/resolve/main/Qwen3-4B-Element18.i1-Q3_K_M.gguf) | i1-Q3_K_M | 2.2 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Element18-i1-GGUF/resolve/main/Qwen3-4B-Element18.i1-Q3_K_L.gguf) | i1-Q3_K_L | 2.3 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Element18-i1-GGUF/resolve/main/Qwen3-4B-Element18.i1-IQ4_XS.gguf) | i1-IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Element18-i1-GGUF/resolve/main/Qwen3-4B-Element18.i1-Q4_0.gguf) | i1-Q4_0 | 2.5 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Element18-i1-GGUF/resolve/main/Qwen3-4B-Element18.i1-IQ4_NL.gguf) | i1-IQ4_NL | 2.5 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Element18-i1-GGUF/resolve/main/Qwen3-4B-Element18.i1-Q4_K_S.gguf) | i1-Q4_K_S | 2.5 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Element18-i1-GGUF/resolve/main/Qwen3-4B-Element18.i1-Q4_K_M.gguf) | i1-Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Element18-i1-GGUF/resolve/main/Qwen3-4B-Element18.i1-Q4_1.gguf) | i1-Q4_1 | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Element18-i1-GGUF/resolve/main/Qwen3-4B-Element18.i1-Q5_K_S.gguf) | i1-Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Element18-i1-GGUF/resolve/main/Qwen3-4B-Element18.i1-Q5_K_M.gguf) | i1-Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Element18-i1-GGUF/resolve/main/Qwen3-4B-Element18.i1-Q6_K.gguf) | i1-Q6_K | 3.4 | 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. + +