commit fbf99f549afef0f3e6f1d9641c47069b2530275e Author: ModelHub XC Date: Thu May 28 00:00:22 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-4B-Sky-High-Hermes-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..dd05512 --- /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-Sky-High-Hermes.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Sky-High-Hermes.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Sky-High-Hermes.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Sky-High-Hermes.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Sky-High-Hermes.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Sky-High-Hermes.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Sky-High-Hermes.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Sky-High-Hermes.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Sky-High-Hermes.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Sky-High-Hermes.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Sky-High-Hermes.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Sky-High-Hermes.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Sky-High-Hermes.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Sky-High-Hermes.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Sky-High-Hermes.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Sky-High-Hermes.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Sky-High-Hermes.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Sky-High-Hermes.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Sky-High-Hermes.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Sky-High-Hermes.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Sky-High-Hermes.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Sky-High-Hermes.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Sky-High-Hermes.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Sky-High-Hermes.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Sky-High-Hermes.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-4B-Sky-High-Hermes.i1-IQ1_M.gguf b/Qwen3-4B-Sky-High-Hermes.i1-IQ1_M.gguf new file mode 100644 index 0000000..896f233 --- /dev/null +++ b/Qwen3-4B-Sky-High-Hermes.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90182d8bbfe6545892fcb64f6d2f74074c7f31b2ca7527d6755a62bedfea293e +size 1126544800 diff --git a/Qwen3-4B-Sky-High-Hermes.i1-IQ1_S.gguf b/Qwen3-4B-Sky-High-Hermes.i1-IQ1_S.gguf new file mode 100644 index 0000000..bce750d --- /dev/null +++ b/Qwen3-4B-Sky-High-Hermes.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77f592f6a076d9ae25b3ce8d383a51424b91f37286e753a6d7ec7bdae25fab78 +size 1054782880 diff --git a/Qwen3-4B-Sky-High-Hermes.i1-IQ2_M.gguf b/Qwen3-4B-Sky-High-Hermes.i1-IQ2_M.gguf new file mode 100644 index 0000000..575124d --- /dev/null +++ b/Qwen3-4B-Sky-High-Hermes.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c28383ae7ea0b3792d6625de71bb70ae9748cff389ca97fc340106eece146ef +size 1512510880 diff --git a/Qwen3-4B-Sky-High-Hermes.i1-IQ2_S.gguf b/Qwen3-4B-Sky-High-Hermes.i1-IQ2_S.gguf new file mode 100644 index 0000000..3b05b1f --- /dev/null +++ b/Qwen3-4B-Sky-High-Hermes.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52a0323735f1260f9a07f0c59739f3097331a29a22bdf66c66a307a6b8077ad7 +size 1416828320 diff --git a/Qwen3-4B-Sky-High-Hermes.i1-IQ2_XS.gguf b/Qwen3-4B-Sky-High-Hermes.i1-IQ2_XS.gguf new file mode 100644 index 0000000..9950e87 --- /dev/null +++ b/Qwen3-4B-Sky-High-Hermes.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80d7a5230a033a144e179324dc4ecac335c908df3863255e8f756b7ec5916719 +size 1353627040 diff --git a/Qwen3-4B-Sky-High-Hermes.i1-IQ2_XXS.gguf b/Qwen3-4B-Sky-High-Hermes.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..f93a8f6 --- /dev/null +++ b/Qwen3-4B-Sky-High-Hermes.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afd000caeaf05c892b1830067ebe36607a1309d1dbac07b8db43d533e0dd6e2e +size 1246148000 diff --git a/Qwen3-4B-Sky-High-Hermes.i1-IQ3_M.gguf b/Qwen3-4B-Sky-High-Hermes.i1-IQ3_M.gguf new file mode 100644 index 0000000..c620a5f --- /dev/null +++ b/Qwen3-4B-Sky-High-Hermes.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0508393a81167194c1d9c73f653e47e063e7076353019ce5dc83e2bcbc8665c9 +size 1962332448 diff --git a/Qwen3-4B-Sky-High-Hermes.i1-IQ3_S.gguf b/Qwen3-4B-Sky-High-Hermes.i1-IQ3_S.gguf new file mode 100644 index 0000000..f3cfb74 --- /dev/null +++ b/Qwen3-4B-Sky-High-Hermes.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79f8cdaa1d1701dcb6c94e3d5cc3498ced4b8a8b9975c1c263ddb00e283a7425 +size 1898967328 diff --git a/Qwen3-4B-Sky-High-Hermes.i1-IQ3_XS.gguf b/Qwen3-4B-Sky-High-Hermes.i1-IQ3_XS.gguf new file mode 100644 index 0000000..0152f00 --- /dev/null +++ b/Qwen3-4B-Sky-High-Hermes.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6cff7d32e9f3bc2df3ff855f85280f1de22525b4a1eab76d42e0552e5483ead7 +size 1813811488 diff --git a/Qwen3-4B-Sky-High-Hermes.i1-IQ3_XXS.gguf b/Qwen3-4B-Sky-High-Hermes.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..bb19ab8 --- /dev/null +++ b/Qwen3-4B-Sky-High-Hermes.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9d487777450733b30be9e676c8b48c40b96d586134ec79b1a78831bb5f2d515 +size 1669715360 diff --git a/Qwen3-4B-Sky-High-Hermes.i1-IQ4_NL.gguf b/Qwen3-4B-Sky-High-Hermes.i1-IQ4_NL.gguf new file mode 100644 index 0000000..43d89e0 --- /dev/null +++ b/Qwen3-4B-Sky-High-Hermes.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93b740fce1b08c155d844e82c0aa74a7b469fa88507046aff555f1b794b148d8 +size 2380779808 diff --git a/Qwen3-4B-Sky-High-Hermes.i1-IQ4_XS.gguf b/Qwen3-4B-Sky-High-Hermes.i1-IQ4_XS.gguf new file mode 100644 index 0000000..0088777 --- /dev/null +++ b/Qwen3-4B-Sky-High-Hermes.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1a4c0a67cfc3510e32bd80967e8f45779080163ae638f2dd1400d9b15b6d127 +size 2270187808 diff --git a/Qwen3-4B-Sky-High-Hermes.i1-Q2_K.gguf b/Qwen3-4B-Sky-High-Hermes.i1-Q2_K.gguf new file mode 100644 index 0000000..84ca9b5 --- /dev/null +++ b/Qwen3-4B-Sky-High-Hermes.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5fb057dd624ef108034a1374159d9424052a0a039f5e3d4a2008b20c148e888c +size 1668935968 diff --git a/Qwen3-4B-Sky-High-Hermes.i1-Q2_K_S.gguf b/Qwen3-4B-Sky-High-Hermes.i1-Q2_K_S.gguf new file mode 100644 index 0000000..a9569cb --- /dev/null +++ b/Qwen3-4B-Sky-High-Hermes.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2654cae09a8b4ea3dd066064cf626eea338a61858e3f2f0afadc132081983b93 +size 1562890528 diff --git a/Qwen3-4B-Sky-High-Hermes.i1-Q3_K_L.gguf b/Qwen3-4B-Sky-High-Hermes.i1-Q3_K_L.gguf new file mode 100644 index 0000000..a293ee2 --- /dev/null +++ b/Qwen3-4B-Sky-High-Hermes.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef76191ece6b13c2bdf8c0adbb34720e66bac6109ca847b87fab548870accb5f +size 2239222048 diff --git a/Qwen3-4B-Sky-High-Hermes.i1-Q3_K_M.gguf b/Qwen3-4B-Sky-High-Hermes.i1-Q3_K_M.gguf new file mode 100644 index 0000000..e53805c --- /dev/null +++ b/Qwen3-4B-Sky-High-Hermes.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b46f7443d1eac9e2826f0a686f091e8b31e49f431f386e9fc0219d6967849fb1 +size 2075054368 diff --git a/Qwen3-4B-Sky-High-Hermes.i1-Q3_K_S.gguf b/Qwen3-4B-Sky-High-Hermes.i1-Q3_K_S.gguf new file mode 100644 index 0000000..f7184f8 --- /dev/null +++ b/Qwen3-4B-Sky-High-Hermes.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1113c60366f7895da1100a67136909d95ca2246e0c2046acb361d95f115b1608 +size 1886433568 diff --git a/Qwen3-4B-Sky-High-Hermes.i1-Q4_0.gguf b/Qwen3-4B-Sky-High-Hermes.i1-Q4_0.gguf new file mode 100644 index 0000000..6e29faf --- /dev/null +++ b/Qwen3-4B-Sky-High-Hermes.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4068853438b8cbe5a4213221b692886df6c758ffcadf0735a2a9813e6144a414 +size 2375209248 diff --git a/Qwen3-4B-Sky-High-Hermes.i1-Q4_1.gguf b/Qwen3-4B-Sky-High-Hermes.i1-Q4_1.gguf new file mode 100644 index 0000000..578351f --- /dev/null +++ b/Qwen3-4B-Sky-High-Hermes.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b16b9ff8d036bda42e2aefdde8a5a8c30275f282095bb1f8258cf1fdc97f3347 +size 2596065568 diff --git a/Qwen3-4B-Sky-High-Hermes.i1-Q4_K_M.gguf b/Qwen3-4B-Sky-High-Hermes.i1-Q4_K_M.gguf new file mode 100644 index 0000000..4e2f36a --- /dev/null +++ b/Qwen3-4B-Sky-High-Hermes.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83c43041a72e318a8e6a6ae18571a27dfce15c4eb98f905b21836d099b2a4c71 +size 2496717088 diff --git a/Qwen3-4B-Sky-High-Hermes.i1-Q4_K_S.gguf b/Qwen3-4B-Sky-High-Hermes.i1-Q4_K_S.gguf new file mode 100644 index 0000000..006810e --- /dev/null +++ b/Qwen3-4B-Sky-High-Hermes.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:505bd5101bfd54a2114c93490ea735802fa7ddca89fc7e44bf018ab31b717aeb +size 2382745888 diff --git a/Qwen3-4B-Sky-High-Hermes.i1-Q5_K_M.gguf b/Qwen3-4B-Sky-High-Hermes.i1-Q5_K_M.gguf new file mode 100644 index 0000000..8cc9ea3 --- /dev/null +++ b/Qwen3-4B-Sky-High-Hermes.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9450a0e77c5f45908bf7aae0a46147f06f17332cbdf412ffb95624199d6cad58 +size 2888950048 diff --git a/Qwen3-4B-Sky-High-Hermes.i1-Q5_K_S.gguf b/Qwen3-4B-Sky-High-Hermes.i1-Q5_K_S.gguf new file mode 100644 index 0000000..8714dfd --- /dev/null +++ b/Qwen3-4B-Sky-High-Hermes.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af23b3a94b60f05b900c969d6000a07ed84fdce11b11d2f494dcb27a5a0fd21c +size 2823147808 diff --git a/Qwen3-4B-Sky-High-Hermes.i1-Q6_K.gguf b/Qwen3-4B-Sky-High-Hermes.i1-Q6_K.gguf new file mode 100644 index 0000000..5182baf --- /dev/null +++ b/Qwen3-4B-Sky-High-Hermes.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dafff69de4f738aeedd65dde40cfc93a28276efe84b2ed953ac6a938baa0fa39 +size 3305697568 diff --git a/Qwen3-4B-Sky-High-Hermes.imatrix.gguf b/Qwen3-4B-Sky-High-Hermes.imatrix.gguf new file mode 100644 index 0000000..0631db5 --- /dev/null +++ b/Qwen3-4B-Sky-High-Hermes.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ff7aa5a2932fd5b3f69cd1aaed82b3cf0963de7971864f26a7db6ce433c1bbe +size 3872640 diff --git a/README.md b/README.md new file mode 100644 index 0000000..8f4818c --- /dev/null +++ b/README.md @@ -0,0 +1,98 @@ +--- +base_model: ZeroXClem/Qwen3-4B-Sky-High-Hermes +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- merge +- mergekit +- lazymergekit +- qwen3 +- ZeroXClem +- hermes +- SkyHighHermes +- Heretic +- Abliterated +- HighReasoning +- Distilled +- Claude +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/ZeroXClem/Qwen3-4B-Sky-High-Hermes + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-4B-Sky-High-Hermes-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Qwen3-4B-Sky-High-Hermes-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-Sky-High-Hermes-i1-GGUF/resolve/main/Qwen3-4B-Sky-High-Hermes.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Sky-High-Hermes-i1-GGUF/resolve/main/Qwen3-4B-Sky-High-Hermes.i1-IQ1_S.gguf) | i1-IQ1_S | 1.2 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Sky-High-Hermes-i1-GGUF/resolve/main/Qwen3-4B-Sky-High-Hermes.i1-IQ1_M.gguf) | i1-IQ1_M | 1.2 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Sky-High-Hermes-i1-GGUF/resolve/main/Qwen3-4B-Sky-High-Hermes.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Sky-High-Hermes-i1-GGUF/resolve/main/Qwen3-4B-Sky-High-Hermes.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Sky-High-Hermes-i1-GGUF/resolve/main/Qwen3-4B-Sky-High-Hermes.i1-IQ2_S.gguf) | i1-IQ2_S | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Sky-High-Hermes-i1-GGUF/resolve/main/Qwen3-4B-Sky-High-Hermes.i1-IQ2_M.gguf) | i1-IQ2_M | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Sky-High-Hermes-i1-GGUF/resolve/main/Qwen3-4B-Sky-High-Hermes.i1-Q2_K_S.gguf) | i1-Q2_K_S | 1.7 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Sky-High-Hermes-i1-GGUF/resolve/main/Qwen3-4B-Sky-High-Hermes.i1-Q2_K.gguf) | i1-Q2_K | 1.8 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Sky-High-Hermes-i1-GGUF/resolve/main/Qwen3-4B-Sky-High-Hermes.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Sky-High-Hermes-i1-GGUF/resolve/main/Qwen3-4B-Sky-High-Hermes.i1-IQ3_XS.gguf) | i1-IQ3_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Sky-High-Hermes-i1-GGUF/resolve/main/Qwen3-4B-Sky-High-Hermes.i1-Q3_K_S.gguf) | i1-Q3_K_S | 2.0 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Sky-High-Hermes-i1-GGUF/resolve/main/Qwen3-4B-Sky-High-Hermes.i1-IQ3_S.gguf) | i1-IQ3_S | 2.0 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Sky-High-Hermes-i1-GGUF/resolve/main/Qwen3-4B-Sky-High-Hermes.i1-IQ3_M.gguf) | i1-IQ3_M | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Sky-High-Hermes-i1-GGUF/resolve/main/Qwen3-4B-Sky-High-Hermes.i1-Q3_K_M.gguf) | i1-Q3_K_M | 2.2 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Sky-High-Hermes-i1-GGUF/resolve/main/Qwen3-4B-Sky-High-Hermes.i1-Q3_K_L.gguf) | i1-Q3_K_L | 2.3 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Sky-High-Hermes-i1-GGUF/resolve/main/Qwen3-4B-Sky-High-Hermes.i1-IQ4_XS.gguf) | i1-IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Sky-High-Hermes-i1-GGUF/resolve/main/Qwen3-4B-Sky-High-Hermes.i1-Q4_0.gguf) | i1-Q4_0 | 2.5 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Sky-High-Hermes-i1-GGUF/resolve/main/Qwen3-4B-Sky-High-Hermes.i1-IQ4_NL.gguf) | i1-IQ4_NL | 2.5 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Sky-High-Hermes-i1-GGUF/resolve/main/Qwen3-4B-Sky-High-Hermes.i1-Q4_K_S.gguf) | i1-Q4_K_S | 2.5 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Sky-High-Hermes-i1-GGUF/resolve/main/Qwen3-4B-Sky-High-Hermes.i1-Q4_K_M.gguf) | i1-Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Sky-High-Hermes-i1-GGUF/resolve/main/Qwen3-4B-Sky-High-Hermes.i1-Q4_1.gguf) | i1-Q4_1 | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Sky-High-Hermes-i1-GGUF/resolve/main/Qwen3-4B-Sky-High-Hermes.i1-Q5_K_S.gguf) | i1-Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Sky-High-Hermes-i1-GGUF/resolve/main/Qwen3-4B-Sky-High-Hermes.i1-Q5_K_M.gguf) | i1-Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Sky-High-Hermes-i1-GGUF/resolve/main/Qwen3-4B-Sky-High-Hermes.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. + +