commit 6329928c1e77c666cdd1d18df15f8a2c32376dc4 Author: ModelHub XC Date: Wed Jul 22 13:14:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-4B-Element8-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c6c627a --- /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-Element8.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Element8.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Element8.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Element8.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Element8.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Element8.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Element8.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Element8.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Element8.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Element8.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Element8.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Element8.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Element8.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Element8.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Element8.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Element8.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Element8.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Element8.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Element8.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Element8.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Element8.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Element8.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Element8.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Element8.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Element8.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-4B-Element8.i1-IQ1_M.gguf b/Qwen3-4B-Element8.i1-IQ1_M.gguf new file mode 100644 index 0000000..fd106f6 --- /dev/null +++ b/Qwen3-4B-Element8.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:470254e50b8eb18d3abddee38e9db41cd8cfafe293bf7173b9a018d3500b85b2 +size 1127026208 diff --git a/Qwen3-4B-Element8.i1-IQ1_S.gguf b/Qwen3-4B-Element8.i1-IQ1_S.gguf new file mode 100644 index 0000000..65ae38e --- /dev/null +++ b/Qwen3-4B-Element8.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5f3c1cc39730ab76eed61f8f7b4e2181de3eff588a80e71cfb61de37598a5c1 +size 1055264288 diff --git a/Qwen3-4B-Element8.i1-IQ2_M.gguf b/Qwen3-4B-Element8.i1-IQ2_M.gguf new file mode 100644 index 0000000..42d14a3 --- /dev/null +++ b/Qwen3-4B-Element8.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bced0936a486ea0b0369d5a82629ba206d50b8473d11c53dc3619a2e3b06b6e +size 1512992288 diff --git a/Qwen3-4B-Element8.i1-IQ2_S.gguf b/Qwen3-4B-Element8.i1-IQ2_S.gguf new file mode 100644 index 0000000..e6c309f --- /dev/null +++ b/Qwen3-4B-Element8.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6024a2f3960dea277947b2e93b1c3a1de9f61c0bfec2cae0e2137fda593034d6 +size 1417309728 diff --git a/Qwen3-4B-Element8.i1-IQ2_XS.gguf b/Qwen3-4B-Element8.i1-IQ2_XS.gguf new file mode 100644 index 0000000..fc0aebf --- /dev/null +++ b/Qwen3-4B-Element8.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9b7aa20f281c8459151e4b11e52ef428b84ab2150782d7e1e4e98791aaa577c +size 1354108448 diff --git a/Qwen3-4B-Element8.i1-IQ2_XXS.gguf b/Qwen3-4B-Element8.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..d2296df --- /dev/null +++ b/Qwen3-4B-Element8.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4bbbdd6b591cacec27a949859c9d1e62af3a91d6751a4dc86867126358ba250 +size 1246629408 diff --git a/Qwen3-4B-Element8.i1-IQ3_M.gguf b/Qwen3-4B-Element8.i1-IQ3_M.gguf new file mode 100644 index 0000000..7e841f8 --- /dev/null +++ b/Qwen3-4B-Element8.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6fcd2b3d629f1246b95c86101af6b8cac0ad2e62df4e226938cc51727da6b4bf +size 1962904608 diff --git a/Qwen3-4B-Element8.i1-IQ3_S.gguf b/Qwen3-4B-Element8.i1-IQ3_S.gguf new file mode 100644 index 0000000..da1a543 --- /dev/null +++ b/Qwen3-4B-Element8.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65aa32f74bed42efbb9b7e128a67f8d496400f2879c39cd712c017e547983c62 +size 1899539488 diff --git a/Qwen3-4B-Element8.i1-IQ3_XS.gguf b/Qwen3-4B-Element8.i1-IQ3_XS.gguf new file mode 100644 index 0000000..8749fef --- /dev/null +++ b/Qwen3-4B-Element8.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2eeb97a231cc68e5045e64d8d657f3eb86c66108a9b3dc8151351c3b068f9f1a +size 1814383648 diff --git a/Qwen3-4B-Element8.i1-IQ3_XXS.gguf b/Qwen3-4B-Element8.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..f39424e --- /dev/null +++ b/Qwen3-4B-Element8.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e7b1cfa37c75f49671cda8fd0b17b05ed1ab9c6fa3cd52d0bd458d93a7d1598 +size 1670196768 diff --git a/Qwen3-4B-Element8.i1-IQ4_NL.gguf b/Qwen3-4B-Element8.i1-IQ4_NL.gguf new file mode 100644 index 0000000..1c3076a --- /dev/null +++ b/Qwen3-4B-Element8.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c103cca6902a31e1ca2ef25d5b0493423dc77952aa023324eff9fd477338a767 +size 2381351968 diff --git a/Qwen3-4B-Element8.i1-IQ4_XS.gguf b/Qwen3-4B-Element8.i1-IQ4_XS.gguf new file mode 100644 index 0000000..b2439e8 --- /dev/null +++ b/Qwen3-4B-Element8.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44f04dbf4cfe313e0221f1d9512bac56bced345789a1aeb383802e319453ef2c +size 2270759968 diff --git a/Qwen3-4B-Element8.i1-Q2_K.gguf b/Qwen3-4B-Element8.i1-Q2_K.gguf new file mode 100644 index 0000000..0440655 --- /dev/null +++ b/Qwen3-4B-Element8.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6eba4d19588617b1912c53167128ea19b1bfbee625b2609b97fa55807eff52c3 +size 1669508128 diff --git a/Qwen3-4B-Element8.i1-Q2_K_S.gguf b/Qwen3-4B-Element8.i1-Q2_K_S.gguf new file mode 100644 index 0000000..7bab7dc --- /dev/null +++ b/Qwen3-4B-Element8.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec25fdf9b354c38946b7fea0a7ec8ae4d8ec0f4da04a102404ee2016887814eb +size 1563462688 diff --git a/Qwen3-4B-Element8.i1-Q3_K_L.gguf b/Qwen3-4B-Element8.i1-Q3_K_L.gguf new file mode 100644 index 0000000..e241dbf --- /dev/null +++ b/Qwen3-4B-Element8.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9627e51f2e03d5d89601aadd3e3bb2efadae29b1451c4544e3b8d748fd2b510d +size 2239794208 diff --git a/Qwen3-4B-Element8.i1-Q3_K_M.gguf b/Qwen3-4B-Element8.i1-Q3_K_M.gguf new file mode 100644 index 0000000..9acb0a6 --- /dev/null +++ b/Qwen3-4B-Element8.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:175fb4a237af4114d85a6796bae3f2132b0117665faaca84acef04e5cf44089e +size 2075626528 diff --git a/Qwen3-4B-Element8.i1-Q3_K_S.gguf b/Qwen3-4B-Element8.i1-Q3_K_S.gguf new file mode 100644 index 0000000..6790abe --- /dev/null +++ b/Qwen3-4B-Element8.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4b426df4b04ceea1c3b465108716c69f6e7ce5ce9089148eb7fa25daf3af897 +size 1887005728 diff --git a/Qwen3-4B-Element8.i1-Q4_0.gguf b/Qwen3-4B-Element8.i1-Q4_0.gguf new file mode 100644 index 0000000..7144a9a --- /dev/null +++ b/Qwen3-4B-Element8.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67cb044d48dbbc381991781a86c1db13d1a952a7a7001957f20ec3c412b4aeb0 +size 2375781408 diff --git a/Qwen3-4B-Element8.i1-Q4_1.gguf b/Qwen3-4B-Element8.i1-Q4_1.gguf new file mode 100644 index 0000000..cbd9915 --- /dev/null +++ b/Qwen3-4B-Element8.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82f7c6e1300e332532a112c218ac64041dec2e35e36946a103db9f9a2d5af85e +size 2596637728 diff --git a/Qwen3-4B-Element8.i1-Q4_K_M.gguf b/Qwen3-4B-Element8.i1-Q4_K_M.gguf new file mode 100644 index 0000000..cf117f6 --- /dev/null +++ b/Qwen3-4B-Element8.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fadece7db386bb22cd66697d2609d6b58578c37043fbfdba71650afae591a98e +size 2497289248 diff --git a/Qwen3-4B-Element8.i1-Q4_K_S.gguf b/Qwen3-4B-Element8.i1-Q4_K_S.gguf new file mode 100644 index 0000000..10f3094 --- /dev/null +++ b/Qwen3-4B-Element8.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69a86bdd028d77a82b98e75cf4e15d1bdbdaa1f67bfb6889c631859836716d49 +size 2383318048 diff --git a/Qwen3-4B-Element8.i1-Q5_K_M.gguf b/Qwen3-4B-Element8.i1-Q5_K_M.gguf new file mode 100644 index 0000000..c50592a --- /dev/null +++ b/Qwen3-4B-Element8.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6888a0ad481142b691ee74ce74124fa157b6617b7f7e4727fab3e3d7ba4fb1d +size 2889522208 diff --git a/Qwen3-4B-Element8.i1-Q5_K_S.gguf b/Qwen3-4B-Element8.i1-Q5_K_S.gguf new file mode 100644 index 0000000..cc33464 --- /dev/null +++ b/Qwen3-4B-Element8.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91120d98c307c8fa54f386053780b2f8bdc5e0b7457a9b54e1129f5559fc46fd +size 2823719968 diff --git a/Qwen3-4B-Element8.i1-Q6_K.gguf b/Qwen3-4B-Element8.i1-Q6_K.gguf new file mode 100644 index 0000000..188ef7f --- /dev/null +++ b/Qwen3-4B-Element8.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc158b8772a38e006eb64e027972abc28d19bf1691f0958a53befda89c7da6bc +size 3306269728 diff --git a/Qwen3-4B-Element8.imatrix.gguf b/Qwen3-4B-Element8.imatrix.gguf new file mode 100644 index 0000000..89488b7 --- /dev/null +++ b/Qwen3-4B-Element8.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba3f750ef591dcf87c35d203b5e12776ac749ea71e1c763727d6a7254f861dd2 +size 3872640 diff --git a/README.md b/README.md new file mode 100644 index 0000000..525a40d --- /dev/null +++ b/README.md @@ -0,0 +1,115 @@ +--- +base_model: nightmedia/Qwen3-4B-Element8 +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 +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/nightmedia/Qwen3-4B-Element8 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-4B-Element8-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Qwen3-4B-Element8-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-Element8-i1-GGUF/resolve/main/Qwen3-4B-Element8.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Element8-i1-GGUF/resolve/main/Qwen3-4B-Element8.i1-IQ1_S.gguf) | i1-IQ1_S | 1.2 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Element8-i1-GGUF/resolve/main/Qwen3-4B-Element8.i1-IQ1_M.gguf) | i1-IQ1_M | 1.2 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Element8-i1-GGUF/resolve/main/Qwen3-4B-Element8.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Element8-i1-GGUF/resolve/main/Qwen3-4B-Element8.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Element8-i1-GGUF/resolve/main/Qwen3-4B-Element8.i1-IQ2_S.gguf) | i1-IQ2_S | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Element8-i1-GGUF/resolve/main/Qwen3-4B-Element8.i1-IQ2_M.gguf) | i1-IQ2_M | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Element8-i1-GGUF/resolve/main/Qwen3-4B-Element8.i1-Q2_K_S.gguf) | i1-Q2_K_S | 1.7 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Element8-i1-GGUF/resolve/main/Qwen3-4B-Element8.i1-Q2_K.gguf) | i1-Q2_K | 1.8 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Element8-i1-GGUF/resolve/main/Qwen3-4B-Element8.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Element8-i1-GGUF/resolve/main/Qwen3-4B-Element8.i1-IQ3_XS.gguf) | i1-IQ3_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Element8-i1-GGUF/resolve/main/Qwen3-4B-Element8.i1-Q3_K_S.gguf) | i1-Q3_K_S | 2.0 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Element8-i1-GGUF/resolve/main/Qwen3-4B-Element8.i1-IQ3_S.gguf) | i1-IQ3_S | 2.0 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Element8-i1-GGUF/resolve/main/Qwen3-4B-Element8.i1-IQ3_M.gguf) | i1-IQ3_M | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Element8-i1-GGUF/resolve/main/Qwen3-4B-Element8.i1-Q3_K_M.gguf) | i1-Q3_K_M | 2.2 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Element8-i1-GGUF/resolve/main/Qwen3-4B-Element8.i1-Q3_K_L.gguf) | i1-Q3_K_L | 2.3 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Element8-i1-GGUF/resolve/main/Qwen3-4B-Element8.i1-IQ4_XS.gguf) | i1-IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Element8-i1-GGUF/resolve/main/Qwen3-4B-Element8.i1-Q4_0.gguf) | i1-Q4_0 | 2.5 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Element8-i1-GGUF/resolve/main/Qwen3-4B-Element8.i1-IQ4_NL.gguf) | i1-IQ4_NL | 2.5 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Element8-i1-GGUF/resolve/main/Qwen3-4B-Element8.i1-Q4_K_S.gguf) | i1-Q4_K_S | 2.5 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Element8-i1-GGUF/resolve/main/Qwen3-4B-Element8.i1-Q4_K_M.gguf) | i1-Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Element8-i1-GGUF/resolve/main/Qwen3-4B-Element8.i1-Q4_1.gguf) | i1-Q4_1 | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Element8-i1-GGUF/resolve/main/Qwen3-4B-Element8.i1-Q5_K_S.gguf) | i1-Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Element8-i1-GGUF/resolve/main/Qwen3-4B-Element8.i1-Q5_K_M.gguf) | i1-Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Element8-i1-GGUF/resolve/main/Qwen3-4B-Element8.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. + +