commit d246775528dfb55b277286ea97c680e4afd629ee Author: ModelHub XC Date: Thu Aug 6 12:37:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Gamunu-4B-Instruct-Alpha-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..8e0baec --- /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 +Gamunu-4B-Instruct-Alpha.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +Gamunu-4B-Instruct-Alpha.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Gamunu-4B-Instruct-Alpha.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Gamunu-4B-Instruct-Alpha.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Gamunu-4B-Instruct-Alpha.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Gamunu-4B-Instruct-Alpha.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Gamunu-4B-Instruct-Alpha.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Gamunu-4B-Instruct-Alpha.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Gamunu-4B-Instruct-Alpha.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Gamunu-4B-Instruct-Alpha.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Gamunu-4B-Instruct-Alpha.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Gamunu-4B-Instruct-Alpha.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Gamunu-4B-Instruct-Alpha.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Gamunu-4B-Instruct-Alpha.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Gamunu-4B-Instruct-Alpha.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Gamunu-4B-Instruct-Alpha.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Gamunu-4B-Instruct-Alpha.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Gamunu-4B-Instruct-Alpha.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Gamunu-4B-Instruct-Alpha.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Gamunu-4B-Instruct-Alpha.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Gamunu-4B-Instruct-Alpha.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Gamunu-4B-Instruct-Alpha.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Gamunu-4B-Instruct-Alpha.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Gamunu-4B-Instruct-Alpha.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Gamunu-4B-Instruct-Alpha.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Gamunu-4B-Instruct-Alpha.i1-IQ1_M.gguf b/Gamunu-4B-Instruct-Alpha.i1-IQ1_M.gguf new file mode 100644 index 0000000..615b44d --- /dev/null +++ b/Gamunu-4B-Instruct-Alpha.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e3056bae6285cd783d33fb7d51bf69eb377e75397d0f690871b162bb945575a +size 1199570208 diff --git a/Gamunu-4B-Instruct-Alpha.i1-IQ1_S.gguf b/Gamunu-4B-Instruct-Alpha.i1-IQ1_S.gguf new file mode 100644 index 0000000..42c8444 --- /dev/null +++ b/Gamunu-4B-Instruct-Alpha.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dce5665eaa21f2f2d7f994f57164d044fd1ac3a39a106d685e894bd6efb3a61f +size 1133092128 diff --git a/Gamunu-4B-Instruct-Alpha.i1-IQ2_M.gguf b/Gamunu-4B-Instruct-Alpha.i1-IQ2_M.gguf new file mode 100644 index 0000000..ff3d3e2 --- /dev/null +++ b/Gamunu-4B-Instruct-Alpha.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9a8e103a31c11f7d4fc6b82a33461f57dfbf55fbe20ea5b4afbbb9ec28f16ce +size 1537981728 diff --git a/Gamunu-4B-Instruct-Alpha.i1-IQ2_S.gguf b/Gamunu-4B-Instruct-Alpha.i1-IQ2_S.gguf new file mode 100644 index 0000000..f11236f --- /dev/null +++ b/Gamunu-4B-Instruct-Alpha.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63f9e5bdda8d57d64e921d56c93346a7f0a4782aac5c71aabb5bf0cc55ce50f2 +size 1449344288 diff --git a/Gamunu-4B-Instruct-Alpha.i1-IQ2_XS.gguf b/Gamunu-4B-Instruct-Alpha.i1-IQ2_XS.gguf new file mode 100644 index 0000000..a1d72b9 --- /dev/null +++ b/Gamunu-4B-Instruct-Alpha.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88d08686226c40021f2a392e6dd7adabbda1f483950a28e10f222f0c978b3ac1 +size 1404575008 diff --git a/Gamunu-4B-Instruct-Alpha.i1-IQ2_XXS.gguf b/Gamunu-4B-Instruct-Alpha.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..b94e671 --- /dev/null +++ b/Gamunu-4B-Instruct-Alpha.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:244fc1d453459eafeaea3fcb3bd5575525bb928643c0c317bbab650b025c4c06 +size 1310367008 diff --git a/Gamunu-4B-Instruct-Alpha.i1-IQ3_M.gguf b/Gamunu-4B-Instruct-Alpha.i1-IQ3_M.gguf new file mode 100644 index 0000000..e06dce1 --- /dev/null +++ b/Gamunu-4B-Instruct-Alpha.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb77257a286dc350711a8ea6c023e5e80109765fe6c83d8aff836bfad1818b27 +size 1986802208 diff --git a/Gamunu-4B-Instruct-Alpha.i1-IQ3_S.gguf b/Gamunu-4B-Instruct-Alpha.i1-IQ3_S.gguf new file mode 100644 index 0000000..47e917e --- /dev/null +++ b/Gamunu-4B-Instruct-Alpha.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4818fc713efd5f09dbc29fa48cb66eb57cace98c8fbc04f4693a9e393dfbda48 +size 1937363488 diff --git a/Gamunu-4B-Instruct-Alpha.i1-IQ3_XS.gguf b/Gamunu-4B-Instruct-Alpha.i1-IQ3_XS.gguf new file mode 100644 index 0000000..b521ddc --- /dev/null +++ b/Gamunu-4B-Instruct-Alpha.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6b122d977c528cd6620ef3c22baa395b9f8af9618e199c52c0d7ba31b786775 +size 1863389728 diff --git a/Gamunu-4B-Instruct-Alpha.i1-IQ3_XXS.gguf b/Gamunu-4B-Instruct-Alpha.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..038ec4d --- /dev/null +++ b/Gamunu-4B-Instruct-Alpha.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:220656cc3b108baf0bda9bfb2b32914ce10301e098a77e1d4c39e29d96a8cf61 +size 1689451808 diff --git a/Gamunu-4B-Instruct-Alpha.i1-IQ4_NL.gguf b/Gamunu-4B-Instruct-Alpha.i1-IQ4_NL.gguf new file mode 100644 index 0000000..80b8cf8 --- /dev/null +++ b/Gamunu-4B-Instruct-Alpha.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:947517833e32193f28ea1a5685b3eb509374185275804f01100b5eb94aea3658 +size 2363511328 diff --git a/Gamunu-4B-Instruct-Alpha.i1-IQ4_XS.gguf b/Gamunu-4B-Instruct-Alpha.i1-IQ4_XS.gguf new file mode 100644 index 0000000..7eb71c8 --- /dev/null +++ b/Gamunu-4B-Instruct-Alpha.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:226adf949bf55214bd02ca5c0b923c71fe1ca90fe897ae2e55c6c3f88823a7f7 +size 2263241248 diff --git a/Gamunu-4B-Instruct-Alpha.i1-Q2_K.gguf b/Gamunu-4B-Instruct-Alpha.i1-Q2_K.gguf new file mode 100644 index 0000000..f2024c8 --- /dev/null +++ b/Gamunu-4B-Instruct-Alpha.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:caa8b7de4e5556b1e0ab3967b7c3da3bb8ff404572bbb071aa5196f62b1a7d10 +size 1729163808 diff --git a/Gamunu-4B-Instruct-Alpha.i1-Q2_K_S.gguf b/Gamunu-4B-Instruct-Alpha.i1-Q2_K_S.gguf new file mode 100644 index 0000000..04db04b --- /dev/null +++ b/Gamunu-4B-Instruct-Alpha.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b16195af6dc4fc3915eaf6fb2fd22fe872181189b412f57d97e0a368fa5e1e05 +size 1636061728 diff --git a/Gamunu-4B-Instruct-Alpha.i1-Q3_K_L.gguf b/Gamunu-4B-Instruct-Alpha.i1-Q3_K_L.gguf new file mode 100644 index 0000000..c64e025 --- /dev/null +++ b/Gamunu-4B-Instruct-Alpha.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72d104df475a37d46d9a129ca483e0ac1eeb7d97e4fce51bab862a930c7e3264 +size 2236084768 diff --git a/Gamunu-4B-Instruct-Alpha.i1-Q3_K_M.gguf b/Gamunu-4B-Instruct-Alpha.i1-Q3_K_M.gguf new file mode 100644 index 0000000..229ff22 --- /dev/null +++ b/Gamunu-4B-Instruct-Alpha.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37aac8f867de003ea66df2d3ae548f09fea1d3413ad06a52fba73727f4b22b9e +size 2098459168 diff --git a/Gamunu-4B-Instruct-Alpha.i1-Q3_K_S.gguf b/Gamunu-4B-Instruct-Alpha.i1-Q3_K_S.gguf new file mode 100644 index 0000000..4bac956 --- /dev/null +++ b/Gamunu-4B-Instruct-Alpha.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6a738421a52fd8001540df067e958b4b4fac676340b041fa1788f092fe46377 +size 1937363488 diff --git a/Gamunu-4B-Instruct-Alpha.i1-Q4_0.gguf b/Gamunu-4B-Instruct-Alpha.i1-Q4_0.gguf new file mode 100644 index 0000000..9d5efb6 --- /dev/null +++ b/Gamunu-4B-Instruct-Alpha.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e19d7bff8788f7d4041e84780f484d6e2d2cfed50e012c9db70efa6389fba39 +size 2370064928 diff --git a/Gamunu-4B-Instruct-Alpha.i1-Q4_1.gguf b/Gamunu-4B-Instruct-Alpha.i1-Q4_1.gguf new file mode 100644 index 0000000..8b7afb5 --- /dev/null +++ b/Gamunu-4B-Instruct-Alpha.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e57442ffa3c194ce817cd7ba8a0c436ca00c2670d03af5f4f3fe73e32f0a7eb +size 2564051488 diff --git a/Gamunu-4B-Instruct-Alpha.i1-Q4_K_M.gguf b/Gamunu-4B-Instruct-Alpha.i1-Q4_K_M.gguf new file mode 100644 index 0000000..c03529f --- /dev/null +++ b/Gamunu-4B-Instruct-Alpha.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2bc6bdd4d0ff8893491306a5dd1cca823699d0c6ccd124d2729d9975dd2fc923 +size 2489893408 diff --git a/Gamunu-4B-Instruct-Alpha.i1-Q4_K_S.gguf b/Gamunu-4B-Instruct-Alpha.i1-Q4_K_S.gguf new file mode 100644 index 0000000..07b653d --- /dev/null +++ b/Gamunu-4B-Instruct-Alpha.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5466f06d0670bfdbb6c8daf3a925e0d079307b3af2d2a91dc627d56995edd79d +size 2377929248 diff --git a/Gamunu-4B-Instruct-Alpha.i1-Q5_K_M.gguf b/Gamunu-4B-Instruct-Alpha.i1-Q5_K_M.gguf new file mode 100644 index 0000000..166f0a0 --- /dev/null +++ b/Gamunu-4B-Instruct-Alpha.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be927fcd4a97372bc83c79519165f8d74186185d442ce4df1014436471189479 +size 2829697568 diff --git a/Gamunu-4B-Instruct-Alpha.i1-Q5_K_S.gguf b/Gamunu-4B-Instruct-Alpha.i1-Q5_K_S.gguf new file mode 100644 index 0000000..a9eb072 --- /dev/null +++ b/Gamunu-4B-Instruct-Alpha.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6cf7cd65b13589eec6ab863628fa49ee11c0163d118f60011648d78044e5117d +size 2764591648 diff --git a/Gamunu-4B-Instruct-Alpha.i1-Q6_K.gguf b/Gamunu-4B-Instruct-Alpha.i1-Q6_K.gguf new file mode 100644 index 0000000..89ca80d --- /dev/null +++ b/Gamunu-4B-Instruct-Alpha.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fcbd82f97df86a1d516a775800d27d839909f97804c5784308c680959ace1e17 +size 3190739488 diff --git a/Gamunu-4B-Instruct-Alpha.imatrix.gguf b/Gamunu-4B-Instruct-Alpha.imatrix.gguf new file mode 100644 index 0000000..8faa39b --- /dev/null +++ b/Gamunu-4B-Instruct-Alpha.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ef130af682db71dadbcc8fe39afa8646334995ed11a83d534d5f52d0c04e34e +size 3448608 diff --git a/README.md b/README.md new file mode 100644 index 0000000..9462328 --- /dev/null +++ b/README.md @@ -0,0 +1,96 @@ +--- +base_model: manthilaffs/Gamunu-4B-Instruct-Alpha +language: +- si +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- instruction-following +- NLP +- question-answering +- reasoning +- academic +- maths +- LK +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/manthilaffs/Gamunu-4B-Instruct-Alpha + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Gamunu-4B-Instruct-Alpha-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Gamunu-4B-Instruct-Alpha-GGUF + +**This is a vision model - mmproj files (if any) will be in the [static repository](https://huggingface.co/mradermacher/Gamunu-4B-Instruct-Alpha-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/Gamunu-4B-Instruct-Alpha-i1-GGUF/resolve/main/Gamunu-4B-Instruct-Alpha.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/Gamunu-4B-Instruct-Alpha-i1-GGUF/resolve/main/Gamunu-4B-Instruct-Alpha.i1-IQ1_S.gguf) | i1-IQ1_S | 1.2 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Gamunu-4B-Instruct-Alpha-i1-GGUF/resolve/main/Gamunu-4B-Instruct-Alpha.i1-IQ1_M.gguf) | i1-IQ1_M | 1.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Gamunu-4B-Instruct-Alpha-i1-GGUF/resolve/main/Gamunu-4B-Instruct-Alpha.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/Gamunu-4B-Instruct-Alpha-i1-GGUF/resolve/main/Gamunu-4B-Instruct-Alpha.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Gamunu-4B-Instruct-Alpha-i1-GGUF/resolve/main/Gamunu-4B-Instruct-Alpha.i1-IQ2_S.gguf) | i1-IQ2_S | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Gamunu-4B-Instruct-Alpha-i1-GGUF/resolve/main/Gamunu-4B-Instruct-Alpha.i1-IQ2_M.gguf) | i1-IQ2_M | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Gamunu-4B-Instruct-Alpha-i1-GGUF/resolve/main/Gamunu-4B-Instruct-Alpha.i1-Q2_K_S.gguf) | i1-Q2_K_S | 1.7 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Gamunu-4B-Instruct-Alpha-i1-GGUF/resolve/main/Gamunu-4B-Instruct-Alpha.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Gamunu-4B-Instruct-Alpha-i1-GGUF/resolve/main/Gamunu-4B-Instruct-Alpha.i1-Q2_K.gguf) | i1-Q2_K | 1.8 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Gamunu-4B-Instruct-Alpha-i1-GGUF/resolve/main/Gamunu-4B-Instruct-Alpha.i1-IQ3_XS.gguf) | i1-IQ3_XS | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Gamunu-4B-Instruct-Alpha-i1-GGUF/resolve/main/Gamunu-4B-Instruct-Alpha.i1-IQ3_S.gguf) | i1-IQ3_S | 2.0 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Gamunu-4B-Instruct-Alpha-i1-GGUF/resolve/main/Gamunu-4B-Instruct-Alpha.i1-Q3_K_S.gguf) | i1-Q3_K_S | 2.0 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Gamunu-4B-Instruct-Alpha-i1-GGUF/resolve/main/Gamunu-4B-Instruct-Alpha.i1-IQ3_M.gguf) | i1-IQ3_M | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/Gamunu-4B-Instruct-Alpha-i1-GGUF/resolve/main/Gamunu-4B-Instruct-Alpha.i1-Q3_K_M.gguf) | i1-Q3_K_M | 2.2 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Gamunu-4B-Instruct-Alpha-i1-GGUF/resolve/main/Gamunu-4B-Instruct-Alpha.i1-Q3_K_L.gguf) | i1-Q3_K_L | 2.3 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Gamunu-4B-Instruct-Alpha-i1-GGUF/resolve/main/Gamunu-4B-Instruct-Alpha.i1-IQ4_XS.gguf) | i1-IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Gamunu-4B-Instruct-Alpha-i1-GGUF/resolve/main/Gamunu-4B-Instruct-Alpha.i1-IQ4_NL.gguf) | i1-IQ4_NL | 2.5 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Gamunu-4B-Instruct-Alpha-i1-GGUF/resolve/main/Gamunu-4B-Instruct-Alpha.i1-Q4_0.gguf) | i1-Q4_0 | 2.5 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Gamunu-4B-Instruct-Alpha-i1-GGUF/resolve/main/Gamunu-4B-Instruct-Alpha.i1-Q4_K_S.gguf) | i1-Q4_K_S | 2.5 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Gamunu-4B-Instruct-Alpha-i1-GGUF/resolve/main/Gamunu-4B-Instruct-Alpha.i1-Q4_K_M.gguf) | i1-Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Gamunu-4B-Instruct-Alpha-i1-GGUF/resolve/main/Gamunu-4B-Instruct-Alpha.i1-Q4_1.gguf) | i1-Q4_1 | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Gamunu-4B-Instruct-Alpha-i1-GGUF/resolve/main/Gamunu-4B-Instruct-Alpha.i1-Q5_K_S.gguf) | i1-Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Gamunu-4B-Instruct-Alpha-i1-GGUF/resolve/main/Gamunu-4B-Instruct-Alpha.i1-Q5_K_M.gguf) | i1-Q5_K_M | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Gamunu-4B-Instruct-Alpha-i1-GGUF/resolve/main/Gamunu-4B-Instruct-Alpha.i1-Q6_K.gguf) | i1-Q6_K | 3.3 | 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. + +