commit b764d81bab2bba0852ffc929e078b4bc2ce152ce Author: ModelHub XC Date: Tue Aug 11 23:01:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Nexa-AI-4B-Instruct-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c73761a --- /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 +Nexa-AI-4B-Instruct.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +Nexa-AI-4B-Instruct.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Nexa-AI-4B-Instruct.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Nexa-AI-4B-Instruct.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Nexa-AI-4B-Instruct.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Nexa-AI-4B-Instruct.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Nexa-AI-4B-Instruct.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Nexa-AI-4B-Instruct.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Nexa-AI-4B-Instruct.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Nexa-AI-4B-Instruct.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Nexa-AI-4B-Instruct.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Nexa-AI-4B-Instruct.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Nexa-AI-4B-Instruct.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Nexa-AI-4B-Instruct.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Nexa-AI-4B-Instruct.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Nexa-AI-4B-Instruct.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Nexa-AI-4B-Instruct.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Nexa-AI-4B-Instruct.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Nexa-AI-4B-Instruct.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Nexa-AI-4B-Instruct.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Nexa-AI-4B-Instruct.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Nexa-AI-4B-Instruct.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Nexa-AI-4B-Instruct.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Nexa-AI-4B-Instruct.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Nexa-AI-4B-Instruct.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Nexa-AI-4B-Instruct.i1-IQ1_M.gguf b/Nexa-AI-4B-Instruct.i1-IQ1_M.gguf new file mode 100644 index 0000000..f34538b --- /dev/null +++ b/Nexa-AI-4B-Instruct.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9fe35474768bb9464365644620a3158e561ed10b656226f523f4ae6a0716971d +size 1127016928 diff --git a/Nexa-AI-4B-Instruct.i1-IQ1_S.gguf b/Nexa-AI-4B-Instruct.i1-IQ1_S.gguf new file mode 100644 index 0000000..e6a964b --- /dev/null +++ b/Nexa-AI-4B-Instruct.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be872082a66bb53d251f8dd61ba92814b27430353947496975b9dc70863884a2 +size 1055255008 diff --git a/Nexa-AI-4B-Instruct.i1-IQ2_M.gguf b/Nexa-AI-4B-Instruct.i1-IQ2_M.gguf new file mode 100644 index 0000000..7b42131 --- /dev/null +++ b/Nexa-AI-4B-Instruct.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60407897f6940b34c3ca117e7c89748a38e48bc8d927f9a96fbe304e73a4a7e7 +size 1512983008 diff --git a/Nexa-AI-4B-Instruct.i1-IQ2_S.gguf b/Nexa-AI-4B-Instruct.i1-IQ2_S.gguf new file mode 100644 index 0000000..ada4def --- /dev/null +++ b/Nexa-AI-4B-Instruct.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04d5210d3e52c65ab9fe00ee408c708e93b14d49bc177d622bf62cfd97f5ab99 +size 1417300448 diff --git a/Nexa-AI-4B-Instruct.i1-IQ2_XS.gguf b/Nexa-AI-4B-Instruct.i1-IQ2_XS.gguf new file mode 100644 index 0000000..32fecff --- /dev/null +++ b/Nexa-AI-4B-Instruct.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bfef1ce63b4443aa57a98f655af9ba4892af68325d5876f922491787ae8e7d7b +size 1354099168 diff --git a/Nexa-AI-4B-Instruct.i1-IQ2_XXS.gguf b/Nexa-AI-4B-Instruct.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..68af3da --- /dev/null +++ b/Nexa-AI-4B-Instruct.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48de8570636b4d3f25f6844a968e2dd5c5138030b02185b777d673c1515b8df7 +size 1246620128 diff --git a/Nexa-AI-4B-Instruct.i1-IQ3_M.gguf b/Nexa-AI-4B-Instruct.i1-IQ3_M.gguf new file mode 100644 index 0000000..ab234bf --- /dev/null +++ b/Nexa-AI-4B-Instruct.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3dfc4d404f89d7f7641871242924b3a08c0f5f118e406f371e09f39ddc501f9 +size 1962895328 diff --git a/Nexa-AI-4B-Instruct.i1-IQ3_S.gguf b/Nexa-AI-4B-Instruct.i1-IQ3_S.gguf new file mode 100644 index 0000000..9a4cb36 --- /dev/null +++ b/Nexa-AI-4B-Instruct.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d922bf2f4111e2f448527f9362692932aa30e08125ced0ee3923ea0d6675794d +size 1899530208 diff --git a/Nexa-AI-4B-Instruct.i1-IQ3_XS.gguf b/Nexa-AI-4B-Instruct.i1-IQ3_XS.gguf new file mode 100644 index 0000000..fd41581 --- /dev/null +++ b/Nexa-AI-4B-Instruct.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9d862fd15e293e5b1434c4cb3b75f62297407a7765ad1484e4e81553befdeb7 +size 1814374368 diff --git a/Nexa-AI-4B-Instruct.i1-IQ3_XXS.gguf b/Nexa-AI-4B-Instruct.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..6bf9f57 --- /dev/null +++ b/Nexa-AI-4B-Instruct.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42fa751a997286675ad5a35dcb0f2424b6dfb0a9d60366dfb5b322130b8ce6d9 +size 1670187488 diff --git a/Nexa-AI-4B-Instruct.i1-IQ4_NL.gguf b/Nexa-AI-4B-Instruct.i1-IQ4_NL.gguf new file mode 100644 index 0000000..f301f7d --- /dev/null +++ b/Nexa-AI-4B-Instruct.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:077ef3898ad804df57bfde67847f022e091d5d6fc3325a643c05eef0bf551d8b +size 2381342688 diff --git a/Nexa-AI-4B-Instruct.i1-IQ4_XS.gguf b/Nexa-AI-4B-Instruct.i1-IQ4_XS.gguf new file mode 100644 index 0000000..b0d8ee6 --- /dev/null +++ b/Nexa-AI-4B-Instruct.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2af6959dd968c0e32b02e806249ed44796dd74143cb32faf0a39dae424d532de +size 2270750688 diff --git a/Nexa-AI-4B-Instruct.i1-Q2_K.gguf b/Nexa-AI-4B-Instruct.i1-Q2_K.gguf new file mode 100644 index 0000000..9863cb2 --- /dev/null +++ b/Nexa-AI-4B-Instruct.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea6cf3b1bacd0a5f2cc7099aadf1464af0fc439560752f758441914eae2423b5 +size 1669498848 diff --git a/Nexa-AI-4B-Instruct.i1-Q2_K_S.gguf b/Nexa-AI-4B-Instruct.i1-Q2_K_S.gguf new file mode 100644 index 0000000..d4640d7 --- /dev/null +++ b/Nexa-AI-4B-Instruct.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:735957cbb25d1fa5f41fb983cc2a7e58213c4e735d131864868fbf9d7af1d584 +size 1563453408 diff --git a/Nexa-AI-4B-Instruct.i1-Q3_K_L.gguf b/Nexa-AI-4B-Instruct.i1-Q3_K_L.gguf new file mode 100644 index 0000000..ac6ce64 --- /dev/null +++ b/Nexa-AI-4B-Instruct.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:119873c7ff60d346183c78f04039be367b0c68b980ab4a109de117a2365c96da +size 2239784928 diff --git a/Nexa-AI-4B-Instruct.i1-Q3_K_M.gguf b/Nexa-AI-4B-Instruct.i1-Q3_K_M.gguf new file mode 100644 index 0000000..2874603 --- /dev/null +++ b/Nexa-AI-4B-Instruct.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c0c904ee8019154c9a4823819486d7a9cd410cd7c6bb5c273f7e2bd2915c169 +size 2075617248 diff --git a/Nexa-AI-4B-Instruct.i1-Q3_K_S.gguf b/Nexa-AI-4B-Instruct.i1-Q3_K_S.gguf new file mode 100644 index 0000000..3716462 --- /dev/null +++ b/Nexa-AI-4B-Instruct.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d865d6ec662f3aafd5b8f17e4631b2c7729667fc91bd195d8c10e51e64285a3 +size 1886996448 diff --git a/Nexa-AI-4B-Instruct.i1-Q4_0.gguf b/Nexa-AI-4B-Instruct.i1-Q4_0.gguf new file mode 100644 index 0000000..f6c3c1a --- /dev/null +++ b/Nexa-AI-4B-Instruct.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd11ee67daa29a3a030ff412bbd38a71e7a19c3743c7edd7ca19e0537815f0e2 +size 2375772128 diff --git a/Nexa-AI-4B-Instruct.i1-Q4_1.gguf b/Nexa-AI-4B-Instruct.i1-Q4_1.gguf new file mode 100644 index 0000000..86c86da --- /dev/null +++ b/Nexa-AI-4B-Instruct.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ffa715e2a2955660acd16bca7f369a3fd9cc92102f9c38c0a9f42b38f8850a78 +size 2596628448 diff --git a/Nexa-AI-4B-Instruct.i1-Q4_K_M.gguf b/Nexa-AI-4B-Instruct.i1-Q4_K_M.gguf new file mode 100644 index 0000000..5dd5ed7 --- /dev/null +++ b/Nexa-AI-4B-Instruct.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e29bc5c645fceb6c20a37229937493ed059e9835f94be669aff933b73d7da2b2 +size 2497279968 diff --git a/Nexa-AI-4B-Instruct.i1-Q4_K_S.gguf b/Nexa-AI-4B-Instruct.i1-Q4_K_S.gguf new file mode 100644 index 0000000..4421f5a --- /dev/null +++ b/Nexa-AI-4B-Instruct.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8569265ad757c33f7c4f216e591685c22628e3145d5b697b41df6a1c27db6257 +size 2383308768 diff --git a/Nexa-AI-4B-Instruct.i1-Q5_K_M.gguf b/Nexa-AI-4B-Instruct.i1-Q5_K_M.gguf new file mode 100644 index 0000000..6e4bd48 --- /dev/null +++ b/Nexa-AI-4B-Instruct.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e105a2b3b033fd1473e3c457c3f6a7d257837b73a64781a43a3f1a4fe7add7e +size 2889512928 diff --git a/Nexa-AI-4B-Instruct.i1-Q5_K_S.gguf b/Nexa-AI-4B-Instruct.i1-Q5_K_S.gguf new file mode 100644 index 0000000..8b90269 --- /dev/null +++ b/Nexa-AI-4B-Instruct.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0dc718c56d2fe3ab2ab6cfd64fde12f8c47cc1d8e1ee81181bf1bb89f9a93478 +size 2823710688 diff --git a/Nexa-AI-4B-Instruct.i1-Q6_K.gguf b/Nexa-AI-4B-Instruct.i1-Q6_K.gguf new file mode 100644 index 0000000..6653cb7 --- /dev/null +++ b/Nexa-AI-4B-Instruct.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:595ea94d985325a31f791cef14bffdddcb2b0aa87ed8243273d72fa678b24b61 +size 3306260448 diff --git a/Nexa-AI-4B-Instruct.imatrix.gguf b/Nexa-AI-4B-Instruct.imatrix.gguf new file mode 100644 index 0000000..3113ce1 --- /dev/null +++ b/Nexa-AI-4B-Instruct.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0c88aa63d300bbcaa901eb2a1a87b329a5c75656b3591d259c8f802b2f508b7 +size 3872640 diff --git a/README.md b/README.md new file mode 100644 index 0000000..b5e2d36 --- /dev/null +++ b/README.md @@ -0,0 +1,97 @@ +--- +base_model: Neura-Tech-AI/Nexa-AI-4B-Instruct +language: +- en +- hi +- zh +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- Neura Tech AI +- Lumina AI +- Nexa AI +- instruct +- llm +- transformer +- qwen +- multilingual +- conversational +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/Neura-Tech-AI/Nexa-AI-4B-Instruct + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Nexa-AI-4B-Instruct-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Nexa-AI-4B-Instruct-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/Nexa-AI-4B-Instruct-i1-GGUF/resolve/main/Nexa-AI-4B-Instruct.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/Nexa-AI-4B-Instruct-i1-GGUF/resolve/main/Nexa-AI-4B-Instruct.i1-IQ1_S.gguf) | i1-IQ1_S | 1.2 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Nexa-AI-4B-Instruct-i1-GGUF/resolve/main/Nexa-AI-4B-Instruct.i1-IQ1_M.gguf) | i1-IQ1_M | 1.2 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Nexa-AI-4B-Instruct-i1-GGUF/resolve/main/Nexa-AI-4B-Instruct.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/Nexa-AI-4B-Instruct-i1-GGUF/resolve/main/Nexa-AI-4B-Instruct.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Nexa-AI-4B-Instruct-i1-GGUF/resolve/main/Nexa-AI-4B-Instruct.i1-IQ2_S.gguf) | i1-IQ2_S | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Nexa-AI-4B-Instruct-i1-GGUF/resolve/main/Nexa-AI-4B-Instruct.i1-IQ2_M.gguf) | i1-IQ2_M | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Nexa-AI-4B-Instruct-i1-GGUF/resolve/main/Nexa-AI-4B-Instruct.i1-Q2_K_S.gguf) | i1-Q2_K_S | 1.7 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Nexa-AI-4B-Instruct-i1-GGUF/resolve/main/Nexa-AI-4B-Instruct.i1-Q2_K.gguf) | i1-Q2_K | 1.8 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Nexa-AI-4B-Instruct-i1-GGUF/resolve/main/Nexa-AI-4B-Instruct.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Nexa-AI-4B-Instruct-i1-GGUF/resolve/main/Nexa-AI-4B-Instruct.i1-IQ3_XS.gguf) | i1-IQ3_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Nexa-AI-4B-Instruct-i1-GGUF/resolve/main/Nexa-AI-4B-Instruct.i1-Q3_K_S.gguf) | i1-Q3_K_S | 2.0 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Nexa-AI-4B-Instruct-i1-GGUF/resolve/main/Nexa-AI-4B-Instruct.i1-IQ3_S.gguf) | i1-IQ3_S | 2.0 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Nexa-AI-4B-Instruct-i1-GGUF/resolve/main/Nexa-AI-4B-Instruct.i1-IQ3_M.gguf) | i1-IQ3_M | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/Nexa-AI-4B-Instruct-i1-GGUF/resolve/main/Nexa-AI-4B-Instruct.i1-Q3_K_M.gguf) | i1-Q3_K_M | 2.2 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Nexa-AI-4B-Instruct-i1-GGUF/resolve/main/Nexa-AI-4B-Instruct.i1-Q3_K_L.gguf) | i1-Q3_K_L | 2.3 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Nexa-AI-4B-Instruct-i1-GGUF/resolve/main/Nexa-AI-4B-Instruct.i1-IQ4_XS.gguf) | i1-IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Nexa-AI-4B-Instruct-i1-GGUF/resolve/main/Nexa-AI-4B-Instruct.i1-Q4_0.gguf) | i1-Q4_0 | 2.5 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Nexa-AI-4B-Instruct-i1-GGUF/resolve/main/Nexa-AI-4B-Instruct.i1-IQ4_NL.gguf) | i1-IQ4_NL | 2.5 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Nexa-AI-4B-Instruct-i1-GGUF/resolve/main/Nexa-AI-4B-Instruct.i1-Q4_K_S.gguf) | i1-Q4_K_S | 2.5 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Nexa-AI-4B-Instruct-i1-GGUF/resolve/main/Nexa-AI-4B-Instruct.i1-Q4_K_M.gguf) | i1-Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Nexa-AI-4B-Instruct-i1-GGUF/resolve/main/Nexa-AI-4B-Instruct.i1-Q4_1.gguf) | i1-Q4_1 | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Nexa-AI-4B-Instruct-i1-GGUF/resolve/main/Nexa-AI-4B-Instruct.i1-Q5_K_S.gguf) | i1-Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Nexa-AI-4B-Instruct-i1-GGUF/resolve/main/Nexa-AI-4B-Instruct.i1-Q5_K_M.gguf) | i1-Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Nexa-AI-4B-Instruct-i1-GGUF/resolve/main/Nexa-AI-4B-Instruct.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. + +