commit 77b65f053f0c273591079d2d7d42af8d1347be4f Author: ModelHub XC Date: Mon Oct 5 06:01:16 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-4B-Diversity-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..933265d --- /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-Diversity.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Diversity.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Diversity.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Diversity.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Diversity.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Diversity.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Diversity.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Diversity.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Diversity.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Diversity.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Diversity.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Diversity.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Diversity.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Diversity.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Diversity.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Diversity.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Diversity.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Diversity.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Diversity.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Diversity.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Diversity.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Diversity.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Diversity.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Diversity.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Diversity.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-4B-Diversity.i1-IQ1_M.gguf b/Qwen3-4B-Diversity.i1-IQ1_M.gguf new file mode 100644 index 0000000..6d7a8b3 --- /dev/null +++ b/Qwen3-4B-Diversity.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8345171b9740dc821a6ab1024f9440341da8d2ff718e8789ab091a5faf399639 +size 1127022240 diff --git a/Qwen3-4B-Diversity.i1-IQ1_S.gguf b/Qwen3-4B-Diversity.i1-IQ1_S.gguf new file mode 100644 index 0000000..f0cfe91 --- /dev/null +++ b/Qwen3-4B-Diversity.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b3193e1d2341379c0be3cc48c2897589d4b51c772d82648748e4dc00f87395c +size 1055260320 diff --git a/Qwen3-4B-Diversity.i1-IQ2_M.gguf b/Qwen3-4B-Diversity.i1-IQ2_M.gguf new file mode 100644 index 0000000..7a72917 --- /dev/null +++ b/Qwen3-4B-Diversity.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6bf00797bb66c38a0739a42cd2355f58978a1252a04602ae0d4b0d77a8ac8d9 +size 1512988320 diff --git a/Qwen3-4B-Diversity.i1-IQ2_S.gguf b/Qwen3-4B-Diversity.i1-IQ2_S.gguf new file mode 100644 index 0000000..32d6703 --- /dev/null +++ b/Qwen3-4B-Diversity.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8cd11a91000d630ca54c6cc81c67561be91b2ca2bbafd30a63755f45bfaeac3f +size 1417305760 diff --git a/Qwen3-4B-Diversity.i1-IQ2_XS.gguf b/Qwen3-4B-Diversity.i1-IQ2_XS.gguf new file mode 100644 index 0000000..563caa1 --- /dev/null +++ b/Qwen3-4B-Diversity.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b87dbd4a5f3f661c55c3838b5727e9657830e2dec625273cb51fa1f16bb83f8 +size 1354104480 diff --git a/Qwen3-4B-Diversity.i1-IQ2_XXS.gguf b/Qwen3-4B-Diversity.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..9f61e63 --- /dev/null +++ b/Qwen3-4B-Diversity.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb9c8c7b53fa70d7a562f2331e8aa0ddf12a1ee92fec8129812a6131622ecaaf +size 1246625440 diff --git a/Qwen3-4B-Diversity.i1-IQ3_M.gguf b/Qwen3-4B-Diversity.i1-IQ3_M.gguf new file mode 100644 index 0000000..4a249b6 --- /dev/null +++ b/Qwen3-4B-Diversity.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27eda8f4ccd23fc8cca0da5577bd5d73ff4a32826059bb44808d99457a89b217 +size 1962900640 diff --git a/Qwen3-4B-Diversity.i1-IQ3_S.gguf b/Qwen3-4B-Diversity.i1-IQ3_S.gguf new file mode 100644 index 0000000..c4d2eab --- /dev/null +++ b/Qwen3-4B-Diversity.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e69b2ab846c624377332cf94b477affe13b2e258ace79688e7c9acf2bbbcf246 +size 1899535520 diff --git a/Qwen3-4B-Diversity.i1-IQ3_XS.gguf b/Qwen3-4B-Diversity.i1-IQ3_XS.gguf new file mode 100644 index 0000000..13d5996 --- /dev/null +++ b/Qwen3-4B-Diversity.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4a8d5ba16b0a5d3268330c4eaa445169f6ff7952cf023e410ea04d65b506746 +size 1814379680 diff --git a/Qwen3-4B-Diversity.i1-IQ3_XXS.gguf b/Qwen3-4B-Diversity.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..6e7cb46 --- /dev/null +++ b/Qwen3-4B-Diversity.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c91753bf482bb5e3779bd396ee267165ac30688862591111f4e65434ab075583 +size 1670192800 diff --git a/Qwen3-4B-Diversity.i1-IQ4_NL.gguf b/Qwen3-4B-Diversity.i1-IQ4_NL.gguf new file mode 100644 index 0000000..df79924 --- /dev/null +++ b/Qwen3-4B-Diversity.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b286a6ee1dc4fc1de6e4f008736487f6363561c510727875a60742c1b5eeb09d +size 2381348000 diff --git a/Qwen3-4B-Diversity.i1-IQ4_XS.gguf b/Qwen3-4B-Diversity.i1-IQ4_XS.gguf new file mode 100644 index 0000000..d965e8c --- /dev/null +++ b/Qwen3-4B-Diversity.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe705235ce21c16d24ac73f7d2d6234ffc086cd1088a38cb32aeb0edf8661272 +size 2270756000 diff --git a/Qwen3-4B-Diversity.i1-Q2_K.gguf b/Qwen3-4B-Diversity.i1-Q2_K.gguf new file mode 100644 index 0000000..7472ebd --- /dev/null +++ b/Qwen3-4B-Diversity.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1904a66baac17ee9957c6920e35dd2df3f7fe50d5ad54d1116f1783a70d650b +size 1669504160 diff --git a/Qwen3-4B-Diversity.i1-Q2_K_S.gguf b/Qwen3-4B-Diversity.i1-Q2_K_S.gguf new file mode 100644 index 0000000..3dc1106 --- /dev/null +++ b/Qwen3-4B-Diversity.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae5cde22b5764bff18a80368c2f46dd8c75ff51bb3ba3ff710d05e2e3c9e38d6 +size 1563458720 diff --git a/Qwen3-4B-Diversity.i1-Q3_K_L.gguf b/Qwen3-4B-Diversity.i1-Q3_K_L.gguf new file mode 100644 index 0000000..e6f58ec --- /dev/null +++ b/Qwen3-4B-Diversity.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0282a4def8acebc48c0a6b8f4c2ab3ffe94ef69e11ef016b9bc8c8caa15038f3 +size 2239790240 diff --git a/Qwen3-4B-Diversity.i1-Q3_K_M.gguf b/Qwen3-4B-Diversity.i1-Q3_K_M.gguf new file mode 100644 index 0000000..d376dbe --- /dev/null +++ b/Qwen3-4B-Diversity.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0f54948cb56a3ed912a566f8226d2862a97bc85f48439fedc145ce8cc3ad2c9 +size 2075622560 diff --git a/Qwen3-4B-Diversity.i1-Q3_K_S.gguf b/Qwen3-4B-Diversity.i1-Q3_K_S.gguf new file mode 100644 index 0000000..5ae3ae6 --- /dev/null +++ b/Qwen3-4B-Diversity.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79518e98b6ba62f32700b417c7220694417343bf1b14f5fa81f4588b1de46c79 +size 1887001760 diff --git a/Qwen3-4B-Diversity.i1-Q4_0.gguf b/Qwen3-4B-Diversity.i1-Q4_0.gguf new file mode 100644 index 0000000..8af8aea --- /dev/null +++ b/Qwen3-4B-Diversity.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:202c1b66c5dd00674f176edef5698e6542657fe98cb86723a2bb490845d1d00a +size 2375777440 diff --git a/Qwen3-4B-Diversity.i1-Q4_1.gguf b/Qwen3-4B-Diversity.i1-Q4_1.gguf new file mode 100644 index 0000000..16dbfc6 --- /dev/null +++ b/Qwen3-4B-Diversity.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6be2ffb37c2762219c336fd7945849c49ec91332f8e8980774e411f33b6aadde +size 2596633760 diff --git a/Qwen3-4B-Diversity.i1-Q4_K_M.gguf b/Qwen3-4B-Diversity.i1-Q4_K_M.gguf new file mode 100644 index 0000000..e4a6367 --- /dev/null +++ b/Qwen3-4B-Diversity.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72be2cc0fa361def78918ab0ccc03f03ed7a0df16b9a42f1b28d951458cd4dac +size 2497285280 diff --git a/Qwen3-4B-Diversity.i1-Q4_K_S.gguf b/Qwen3-4B-Diversity.i1-Q4_K_S.gguf new file mode 100644 index 0000000..a4e1ce9 --- /dev/null +++ b/Qwen3-4B-Diversity.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83a0a51a62698afbad6d6d9b46e36383f0af9ed50682e99b609b54b43b21a663 +size 2383314080 diff --git a/Qwen3-4B-Diversity.i1-Q5_K_M.gguf b/Qwen3-4B-Diversity.i1-Q5_K_M.gguf new file mode 100644 index 0000000..6eb54f6 --- /dev/null +++ b/Qwen3-4B-Diversity.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55baa5076a6fcd7717886c18f4fce6f10b88bcad8f801405689ad3d9a99bed54 +size 2889518240 diff --git a/Qwen3-4B-Diversity.i1-Q5_K_S.gguf b/Qwen3-4B-Diversity.i1-Q5_K_S.gguf new file mode 100644 index 0000000..a89b039 --- /dev/null +++ b/Qwen3-4B-Diversity.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aadf9707a16e11c48a1f894e79d3f2987c9ca1bc7635c8032f9cbeca28c11423 +size 2823716000 diff --git a/Qwen3-4B-Diversity.i1-Q6_K.gguf b/Qwen3-4B-Diversity.i1-Q6_K.gguf new file mode 100644 index 0000000..e489011 --- /dev/null +++ b/Qwen3-4B-Diversity.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:013dd7be0efe5889929a37958b790bbbb3814c28d3b2c5aa65acdb60f4fb7ad9 +size 3306265760 diff --git a/Qwen3-4B-Diversity.imatrix.gguf b/Qwen3-4B-Diversity.imatrix.gguf new file mode 100644 index 0000000..41bddf6 --- /dev/null +++ b/Qwen3-4B-Diversity.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5c8d927cf74ba26f67f0dd510c9b7ac9ff557fb23a3a65700f45be47334adbb +size 3872640 diff --git a/README.md b/README.md new file mode 100644 index 0000000..2eb25bd --- /dev/null +++ b/README.md @@ -0,0 +1,108 @@ +--- +base_model: hadadxyz/Qwen3-4B-Diversity +datasets: +- ianncity/KIMI-K2.5-550000x +- Jackrong/Qwen3.5-reasoning-700x +- nohurry/Opus-4.6-Reasoning-3000x-filtered +- TeichAI/claude-4.5-opus-high-reasoning-250x +- TeichAI/gemini-3-pro-preview-high-reasoning-250x +- TeichAI/claude-haiku-4.5-high-reasoning-1700x +- TeichAI/gpt-5.2-high-reasoning-250x +- Roman1111111/gemini-3.1-pro-hard-high-reasoning +- Jackrong/glm-4.7-multiturn-CoT +- bmeyer2025/glm5-reasoning-traces +- TeichAI/claude-sonnet-4.5-high-reasoning-250x +- TeichAI/deepseek-v3.2-speciale-openr1-math-3k +- TeichAI/deepseek-v3.2-speciale-OpenCodeReasoning-3k +- TeichAI/deepseek-v3.2-speciale-1000x +- TeichAI/gpt-5-codex-1000x +language: +- en +library_name: transformers +license: apache-2.0 +license_link: https://huggingface.co/hadadxyz/Qwen3-4B-Diversity/blob/main/LICENSE +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- distillation +- distilled +- sft +- peft +- qwen3 +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/hadadxyz/Qwen3-4B-Diversity + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-4B-Diversity-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Qwen3-4B-Diversity-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-Diversity-i1-GGUF/resolve/main/Qwen3-4B-Diversity.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Diversity-i1-GGUF/resolve/main/Qwen3-4B-Diversity.i1-IQ1_S.gguf) | i1-IQ1_S | 1.2 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Diversity-i1-GGUF/resolve/main/Qwen3-4B-Diversity.i1-IQ1_M.gguf) | i1-IQ1_M | 1.2 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Diversity-i1-GGUF/resolve/main/Qwen3-4B-Diversity.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Diversity-i1-GGUF/resolve/main/Qwen3-4B-Diversity.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Diversity-i1-GGUF/resolve/main/Qwen3-4B-Diversity.i1-IQ2_S.gguf) | i1-IQ2_S | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Diversity-i1-GGUF/resolve/main/Qwen3-4B-Diversity.i1-IQ2_M.gguf) | i1-IQ2_M | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Diversity-i1-GGUF/resolve/main/Qwen3-4B-Diversity.i1-Q2_K_S.gguf) | i1-Q2_K_S | 1.7 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Diversity-i1-GGUF/resolve/main/Qwen3-4B-Diversity.i1-Q2_K.gguf) | i1-Q2_K | 1.8 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Diversity-i1-GGUF/resolve/main/Qwen3-4B-Diversity.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Diversity-i1-GGUF/resolve/main/Qwen3-4B-Diversity.i1-IQ3_XS.gguf) | i1-IQ3_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Diversity-i1-GGUF/resolve/main/Qwen3-4B-Diversity.i1-Q3_K_S.gguf) | i1-Q3_K_S | 2.0 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Diversity-i1-GGUF/resolve/main/Qwen3-4B-Diversity.i1-IQ3_S.gguf) | i1-IQ3_S | 2.0 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Diversity-i1-GGUF/resolve/main/Qwen3-4B-Diversity.i1-IQ3_M.gguf) | i1-IQ3_M | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Diversity-i1-GGUF/resolve/main/Qwen3-4B-Diversity.i1-Q3_K_M.gguf) | i1-Q3_K_M | 2.2 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Diversity-i1-GGUF/resolve/main/Qwen3-4B-Diversity.i1-Q3_K_L.gguf) | i1-Q3_K_L | 2.3 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Diversity-i1-GGUF/resolve/main/Qwen3-4B-Diversity.i1-IQ4_XS.gguf) | i1-IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Diversity-i1-GGUF/resolve/main/Qwen3-4B-Diversity.i1-Q4_0.gguf) | i1-Q4_0 | 2.5 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Diversity-i1-GGUF/resolve/main/Qwen3-4B-Diversity.i1-IQ4_NL.gguf) | i1-IQ4_NL | 2.5 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Diversity-i1-GGUF/resolve/main/Qwen3-4B-Diversity.i1-Q4_K_S.gguf) | i1-Q4_K_S | 2.5 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Diversity-i1-GGUF/resolve/main/Qwen3-4B-Diversity.i1-Q4_K_M.gguf) | i1-Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Diversity-i1-GGUF/resolve/main/Qwen3-4B-Diversity.i1-Q4_1.gguf) | i1-Q4_1 | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Diversity-i1-GGUF/resolve/main/Qwen3-4B-Diversity.i1-Q5_K_S.gguf) | i1-Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Diversity-i1-GGUF/resolve/main/Qwen3-4B-Diversity.i1-Q5_K_M.gguf) | i1-Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Diversity-i1-GGUF/resolve/main/Qwen3-4B-Diversity.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. + +