commit bf9324e97d1938e28a0aad51fa7102847d10211d Author: ModelHub XC Date: Mon Apr 20 05:07:44 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Dolphin3.0-Llama3.2-3B-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..db50aa8 --- /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 +imatrix.dat filter=lfs diff=lfs merge=lfs -text +Dolphin3.0-Llama3.2-3B.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin3.0-Llama3.2-3B.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin3.0-Llama3.2-3B.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin3.0-Llama3.2-3B.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin3.0-Llama3.2-3B.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin3.0-Llama3.2-3B.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin3.0-Llama3.2-3B.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin3.0-Llama3.2-3B.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin3.0-Llama3.2-3B.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin3.0-Llama3.2-3B.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin3.0-Llama3.2-3B.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin3.0-Llama3.2-3B.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin3.0-Llama3.2-3B.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin3.0-Llama3.2-3B.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin3.0-Llama3.2-3B.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin3.0-Llama3.2-3B.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin3.0-Llama3.2-3B.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin3.0-Llama3.2-3B.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin3.0-Llama3.2-3B.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin3.0-Llama3.2-3B.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin3.0-Llama3.2-3B.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin3.0-Llama3.2-3B.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin3.0-Llama3.2-3B.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin3.0-Llama3.2-3B.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Dolphin3.0-Llama3.2-3B.i1-IQ1_M.gguf b/Dolphin3.0-Llama3.2-3B.i1-IQ1_M.gguf new file mode 100644 index 0000000..db4f0c0 --- /dev/null +++ b/Dolphin3.0-Llama3.2-3B.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d90a71d6b117e4bc1559c0c397aeb5ed6c821bb464128961d2d09e1a9979cc6 +size 924195552 diff --git a/Dolphin3.0-Llama3.2-3B.i1-IQ1_S.gguf b/Dolphin3.0-Llama3.2-3B.i1-IQ1_S.gguf new file mode 100644 index 0000000..11d01e2 --- /dev/null +++ b/Dolphin3.0-Llama3.2-3B.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:039fc8769946fd18a2b69908e70eceeb06445936fdc264f5306c9dde96ac7a3e +size 868162272 diff --git a/Dolphin3.0-Llama3.2-3B.i1-IQ2_M.gguf b/Dolphin3.0-Llama3.2-3B.i1-IQ2_M.gguf new file mode 100644 index 0000000..a1af20c --- /dev/null +++ b/Dolphin3.0-Llama3.2-3B.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b94f6fe2b65b9b2f88c09a0a5ae8fd7317faaf3d8be14c57a7e5c7eab44d5f8 +size 1229036256 diff --git a/Dolphin3.0-Llama3.2-3B.i1-IQ2_S.gguf b/Dolphin3.0-Llama3.2-3B.i1-IQ2_S.gguf new file mode 100644 index 0000000..4d2bb01 --- /dev/null +++ b/Dolphin3.0-Llama3.2-3B.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4ea162963e287b5660c812269217ed54d047874e623862ee150bd0f8a761763 +size 1154325216 diff --git a/Dolphin3.0-Llama3.2-3B.i1-IQ2_XS.gguf b/Dolphin3.0-Llama3.2-3B.i1-IQ2_XS.gguf new file mode 100644 index 0000000..01a005d --- /dev/null +++ b/Dolphin3.0-Llama3.2-3B.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dfbb5dd90c1f60cb7b6beffd4b95e3a5252f7904032899d7daae88744b75536d +size 1100552928 diff --git a/Dolphin3.0-Llama3.2-3B.i1-IQ2_XXS.gguf b/Dolphin3.0-Llama3.2-3B.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..ea37583 --- /dev/null +++ b/Dolphin3.0-Llama3.2-3B.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1a0bd78e897954c458d73305cff48e6e041bd8bf0996daf5437c309915814d6 +size 1017584352 diff --git a/Dolphin3.0-Llama3.2-3B.i1-IQ3_M.gguf b/Dolphin3.0-Llama3.2-3B.i1-IQ3_M.gguf new file mode 100644 index 0000000..d74d615 --- /dev/null +++ b/Dolphin3.0-Llama3.2-3B.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f28ae625c093ed658500c1b5d565535875529052bb055171b7f490d5dcbb45b8 +size 1599673888 diff --git a/Dolphin3.0-Llama3.2-3B.i1-IQ3_S.gguf b/Dolphin3.0-Llama3.2-3B.i1-IQ3_S.gguf new file mode 100644 index 0000000..04496d8 --- /dev/null +++ b/Dolphin3.0-Llama3.2-3B.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8646b0db254406bcaf9af51129787e03d178dad16cf801f67321341c34b213f1 +size 1542854176 diff --git a/Dolphin3.0-Llama3.2-3B.i1-IQ3_XS.gguf b/Dolphin3.0-Llama3.2-3B.i1-IQ3_XS.gguf new file mode 100644 index 0000000..ccc3846 --- /dev/null +++ b/Dolphin3.0-Llama3.2-3B.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1dbeaa78b842d21536be61d7c2f9adfc44bbd283fbe15cc06de19dc167e1c861 +size 1476793888 diff --git a/Dolphin3.0-Llama3.2-3B.i1-IQ3_XXS.gguf b/Dolphin3.0-Llama3.2-3B.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..a59682c --- /dev/null +++ b/Dolphin3.0-Llama3.2-3B.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0eaa5c4649e81984c29a65f355fb844fd258ddf30206676f810054f10c339e99 +size 1348770528 diff --git a/Dolphin3.0-Llama3.2-3B.i1-IQ4_NL.gguf b/Dolphin3.0-Llama3.2-3B.i1-IQ4_NL.gguf new file mode 100644 index 0000000..ac52918 --- /dev/null +++ b/Dolphin3.0-Llama3.2-3B.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95d67c677ba7e195eba565a0d527ed197d4a15eae3440c682f3548d82c94dc5e +size 1917195808 diff --git a/Dolphin3.0-Llama3.2-3B.i1-IQ4_XS.gguf b/Dolphin3.0-Llama3.2-3B.i1-IQ4_XS.gguf new file mode 100644 index 0000000..b17867d --- /dev/null +++ b/Dolphin3.0-Llama3.2-3B.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8602f977aecf36e7f4b453f7f95681e4965f599d5dc1664c0ae4fba21f4cc120 +size 1829115424 diff --git a/Dolphin3.0-Llama3.2-3B.i1-Q2_K.gguf b/Dolphin3.0-Llama3.2-3B.i1-Q2_K.gguf new file mode 100644 index 0000000..45aa9db --- /dev/null +++ b/Dolphin3.0-Llama3.2-3B.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bf63dcfec1c915a2fb7fa999557bd577ea0af7183bcabef4332f667b2d91bfe +size 1363940896 diff --git a/Dolphin3.0-Llama3.2-3B.i1-Q2_K_S.gguf b/Dolphin3.0-Llama3.2-3B.i1-Q2_K_S.gguf new file mode 100644 index 0000000..c2ace10 --- /dev/null +++ b/Dolphin3.0-Llama3.2-3B.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0f5caec76cd57ad06319b4b48274ec8d3001f141a17c46685ea06783255301d +size 1274287648 diff --git a/Dolphin3.0-Llama3.2-3B.i1-Q3_K_L.gguf b/Dolphin3.0-Llama3.2-3B.i1-Q3_K_L.gguf new file mode 100644 index 0000000..68945fa --- /dev/null +++ b/Dolphin3.0-Llama3.2-3B.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c256d0df4a812979b08938efed4873070cfb0d82c578d9826fbc31593b77dac0 +size 1815352864 diff --git a/Dolphin3.0-Llama3.2-3B.i1-Q3_K_M.gguf b/Dolphin3.0-Llama3.2-3B.i1-Q3_K_M.gguf new file mode 100644 index 0000000..a07735a --- /dev/null +++ b/Dolphin3.0-Llama3.2-3B.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef54cfb8bd4f682419720b1bf9169be4a37175b137bd2013ff3f1f15635a4416 +size 1687164448 diff --git a/Dolphin3.0-Llama3.2-3B.i1-Q3_K_S.gguf b/Dolphin3.0-Llama3.2-3B.i1-Q3_K_S.gguf new file mode 100644 index 0000000..f735690 --- /dev/null +++ b/Dolphin3.0-Llama3.2-3B.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:846c57d2472c2a7d1eaaacbaa719a463a7ecc944e1fa4ee58b34f4ff66dbf933 +size 1542854176 diff --git a/Dolphin3.0-Llama3.2-3B.i1-Q4_0.gguf b/Dolphin3.0-Llama3.2-3B.i1-Q4_0.gguf new file mode 100644 index 0000000..4f105cd --- /dev/null +++ b/Dolphin3.0-Llama3.2-3B.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff95ba8a2f8bbbf7aa866b8e9a86225f7c329065921ced3a27fef6abddaa6610 +size 1921914400 diff --git a/Dolphin3.0-Llama3.2-3B.i1-Q4_1.gguf b/Dolphin3.0-Llama3.2-3B.i1-Q4_1.gguf new file mode 100644 index 0000000..afcaf3f --- /dev/null +++ b/Dolphin3.0-Llama3.2-3B.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9274f12a4327556e07509b7d19924202c25b7773631c27089aac4f8dc2355f1b +size 2093356576 diff --git a/Dolphin3.0-Llama3.2-3B.i1-Q4_K_M.gguf b/Dolphin3.0-Llama3.2-3B.i1-Q4_K_M.gguf new file mode 100644 index 0000000..d084a25 --- /dev/null +++ b/Dolphin3.0-Llama3.2-3B.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0961ddf8ea3c3dede2b271f8b28e59750e6ee0d5a93d23cebeea3c25ad99f02 +size 2019382816 diff --git a/Dolphin3.0-Llama3.2-3B.i1-Q4_K_S.gguf b/Dolphin3.0-Llama3.2-3B.i1-Q4_K_S.gguf new file mode 100644 index 0000000..395bc4e --- /dev/null +++ b/Dolphin3.0-Llama3.2-3B.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54c607973e005f84a60db1c754030cc8fa5f4f81913de7ef6cdd251f284c7f91 +size 1928205856 diff --git a/Dolphin3.0-Llama3.2-3B.i1-Q5_K_M.gguf b/Dolphin3.0-Llama3.2-3B.i1-Q5_K_M.gguf new file mode 100644 index 0000000..7dd797e --- /dev/null +++ b/Dolphin3.0-Llama3.2-3B.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:807bf21130acb0cfe5c6899371fb117c8538f68021e972024c85ef476152c412 +size 2322159136 diff --git a/Dolphin3.0-Llama3.2-3B.i1-Q5_K_S.gguf b/Dolphin3.0-Llama3.2-3B.i1-Q5_K_S.gguf new file mode 100644 index 0000000..9d38b6b --- /dev/null +++ b/Dolphin3.0-Llama3.2-3B.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77ae4554f605f6a799a7bce4aeab93e33deb3ddf41f2d078d210a099e40accf4 +size 2269517344 diff --git a/Dolphin3.0-Llama3.2-3B.i1-Q6_K.gguf b/Dolphin3.0-Llama3.2-3B.i1-Q6_K.gguf new file mode 100644 index 0000000..8bee249 --- /dev/null +++ b/Dolphin3.0-Llama3.2-3B.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ea4e2468e85f2791063aaf921e107dea77c31eec4a77e3ecb471528730fcd33 +size 2643858976 diff --git a/README.md b/README.md new file mode 100644 index 0000000..33d6f4a --- /dev/null +++ b/README.md @@ -0,0 +1,95 @@ +--- +base_model: dphn/Dolphin3.0-Llama3.2-3B +datasets: +- OpenCoder-LLM/opc-sft-stage1 +- OpenCoder-LLM/opc-sft-stage2 +- microsoft/orca-agentinstruct-1M-v1 +- microsoft/orca-math-word-problems-200k +- NousResearch/hermes-function-calling-v1 +- AI-MO/NuminaMath-CoT +- AI-MO/NuminaMath-TIR +- allenai/tulu-3-sft-mixture +- cognitivecomputations/dolphin-coder +- HuggingFaceTB/smoltalk +- cognitivecomputations/samantha-data +- m-a-p/CodeFeedback-Filtered-Instruction +- m-a-p/Code-Feedback +language: +- en +library_name: transformers +license: llama3.2 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/dphn/Dolphin3.0-Llama3.2-3B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Dolphin3.0-Llama3.2-3B-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Dolphin3.0-Llama3.2-3B-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/Dolphin3.0-Llama3.2-3B-i1-GGUF/resolve/main/Dolphin3.0-Llama3.2-3B.i1-IQ1_S.gguf) | i1-IQ1_S | 1.0 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Dolphin3.0-Llama3.2-3B-i1-GGUF/resolve/main/Dolphin3.0-Llama3.2-3B.i1-IQ1_M.gguf) | i1-IQ1_M | 1.0 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Dolphin3.0-Llama3.2-3B-i1-GGUF/resolve/main/Dolphin3.0-Llama3.2-3B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/Dolphin3.0-Llama3.2-3B-i1-GGUF/resolve/main/Dolphin3.0-Llama3.2-3B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Dolphin3.0-Llama3.2-3B-i1-GGUF/resolve/main/Dolphin3.0-Llama3.2-3B.i1-IQ2_S.gguf) | i1-IQ2_S | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/Dolphin3.0-Llama3.2-3B-i1-GGUF/resolve/main/Dolphin3.0-Llama3.2-3B.i1-IQ2_M.gguf) | i1-IQ2_M | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/Dolphin3.0-Llama3.2-3B-i1-GGUF/resolve/main/Dolphin3.0-Llama3.2-3B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 1.4 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Dolphin3.0-Llama3.2-3B-i1-GGUF/resolve/main/Dolphin3.0-Llama3.2-3B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Dolphin3.0-Llama3.2-3B-i1-GGUF/resolve/main/Dolphin3.0-Llama3.2-3B.i1-Q2_K.gguf) | i1-Q2_K | 1.5 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Dolphin3.0-Llama3.2-3B-i1-GGUF/resolve/main/Dolphin3.0-Llama3.2-3B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Dolphin3.0-Llama3.2-3B-i1-GGUF/resolve/main/Dolphin3.0-Llama3.2-3B.i1-IQ3_S.gguf) | i1-IQ3_S | 1.6 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Dolphin3.0-Llama3.2-3B-i1-GGUF/resolve/main/Dolphin3.0-Llama3.2-3B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 1.6 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Dolphin3.0-Llama3.2-3B-i1-GGUF/resolve/main/Dolphin3.0-Llama3.2-3B.i1-IQ3_M.gguf) | i1-IQ3_M | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/Dolphin3.0-Llama3.2-3B-i1-GGUF/resolve/main/Dolphin3.0-Llama3.2-3B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 1.8 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Dolphin3.0-Llama3.2-3B-i1-GGUF/resolve/main/Dolphin3.0-Llama3.2-3B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 1.9 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Dolphin3.0-Llama3.2-3B-i1-GGUF/resolve/main/Dolphin3.0-Llama3.2-3B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Dolphin3.0-Llama3.2-3B-i1-GGUF/resolve/main/Dolphin3.0-Llama3.2-3B.i1-IQ4_NL.gguf) | i1-IQ4_NL | 2.0 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Dolphin3.0-Llama3.2-3B-i1-GGUF/resolve/main/Dolphin3.0-Llama3.2-3B.i1-Q4_0.gguf) | i1-Q4_0 | 2.0 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Dolphin3.0-Llama3.2-3B-i1-GGUF/resolve/main/Dolphin3.0-Llama3.2-3B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 2.0 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Dolphin3.0-Llama3.2-3B-i1-GGUF/resolve/main/Dolphin3.0-Llama3.2-3B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Dolphin3.0-Llama3.2-3B-i1-GGUF/resolve/main/Dolphin3.0-Llama3.2-3B.i1-Q4_1.gguf) | i1-Q4_1 | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/Dolphin3.0-Llama3.2-3B-i1-GGUF/resolve/main/Dolphin3.0-Llama3.2-3B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Dolphin3.0-Llama3.2-3B-i1-GGUF/resolve/main/Dolphin3.0-Llama3.2-3B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Dolphin3.0-Llama3.2-3B-i1-GGUF/resolve/main/Dolphin3.0-Llama3.2-3B.i1-Q6_K.gguf) | i1-Q6_K | 2.7 | 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. + + diff --git a/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..f1cdf8d --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:185cc27f53b8f706e09546531667ac5d841d161231be1cf6af8fcd581bed8806 +size 2988377