commit 6ecc66d5a1e8493485ef02020b786ce399ce3a91 Author: ModelHub XC Date: Mon Apr 20 08:14:48 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/QuantuMinx_4B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e076e7c --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.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 +QuantuMinx_4B.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +QuantuMinx_4B.f16.gguf filter=lfs diff=lfs merge=lfs -text +QuantuMinx_4B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +QuantuMinx_4B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +QuantuMinx_4B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +QuantuMinx_4B.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +QuantuMinx_4B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +QuantuMinx_4B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +QuantuMinx_4B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +QuantuMinx_4B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +QuantuMinx_4B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +QuantuMinx_4B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +QuantuMinx_4B.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +QuantuMinx_4B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +QuantuMinx_4B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/QuantuMinx_4B.IQ3_M.gguf b/QuantuMinx_4B.IQ3_M.gguf new file mode 100644 index 0000000..8a06acf --- /dev/null +++ b/QuantuMinx_4B.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc42f1b3743a5618966a7afd0240dd9102db43cbb02a7ffb692f1e861e2f64ad +size 2183415008 diff --git a/QuantuMinx_4B.IQ3_S.gguf b/QuantuMinx_4B.IQ3_S.gguf new file mode 100644 index 0000000..87fb966 --- /dev/null +++ b/QuantuMinx_4B.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd98ae927e105bcb00ac6620318be1d3de50cbe5bb82eeacccc2954fae429d17 +size 2114897120 diff --git a/QuantuMinx_4B.IQ3_XS.gguf b/QuantuMinx_4B.IQ3_XS.gguf new file mode 100644 index 0000000..340e3d0 --- /dev/null +++ b/QuantuMinx_4B.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b530fae2f1cfb19d050b42f3a00cf7ef1e07f9ddc0a0c812b86831959cfaab2c +size 2027603168 diff --git a/QuantuMinx_4B.IQ4_XS.gguf b/QuantuMinx_4B.IQ4_XS.gguf new file mode 100644 index 0000000..cede03c --- /dev/null +++ b/QuantuMinx_4B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:945b3319c217050b206ca905e1ae7e24973a4bb53af498548982e86fb45ab5b6 +size 2553240800 diff --git a/QuantuMinx_4B.Q2_K.gguf b/QuantuMinx_4B.Q2_K.gguf new file mode 100644 index 0000000..d024ab0 --- /dev/null +++ b/QuantuMinx_4B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5788807cadf1862448f98e84ae05b6ea3d7765ef43752703dd18d2225067165 +size 1839738080 diff --git a/QuantuMinx_4B.Q3_K_L.gguf b/QuantuMinx_4B.Q3_K_L.gguf new file mode 100644 index 0000000..b73eb60 --- /dev/null +++ b/QuantuMinx_4B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55ac0c0d1ecac07850e2f9b56b4982fc540d00511a48a954dd13af025e285afa +size 2464859360 diff --git a/QuantuMinx_4B.Q3_K_M.gguf b/QuantuMinx_4B.Q3_K_M.gguf new file mode 100644 index 0000000..addbd71 --- /dev/null +++ b/QuantuMinx_4B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61c68058ae41c04a5b6bd496fd2d143bae2770726d7c04a16be6577e1ae81b80 +size 2296562912 diff --git a/QuantuMinx_4B.Q3_K_S.gguf b/QuantuMinx_4B.Q3_K_S.gguf new file mode 100644 index 0000000..6a6813a --- /dev/null +++ b/QuantuMinx_4B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3fa4066eecd8cd0110812f90ed7254437c28a9e93385a0f0b62d2edad68a2f6 +size 2101527776 diff --git a/QuantuMinx_4B.Q4_K_M.gguf b/QuantuMinx_4B.Q4_K_M.gguf new file mode 100644 index 0000000..f8e74f8 --- /dev/null +++ b/QuantuMinx_4B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a139602f65e7c2d04816ae537a5e911c639f47af7781a5a1374c8e38d4c4860d +size 2778283232 diff --git a/QuantuMinx_4B.Q4_K_S.gguf b/QuantuMinx_4B.Q4_K_S.gguf new file mode 100644 index 0000000..1345a8a --- /dev/null +++ b/QuantuMinx_4B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e716a149564b9459cceff5e214aabedca02fb4bf410947de0850c8095f672a7 +size 2664250592 diff --git a/QuantuMinx_4B.Q5_K_M.gguf b/QuantuMinx_4B.Q5_K_M.gguf new file mode 100644 index 0000000..0607d12 --- /dev/null +++ b/QuantuMinx_4B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b33731810443418e677dfac8bd1532d12a74846f7fcf994598a7bd9dcfb5f46 +size 3230186720 diff --git a/QuantuMinx_4B.Q5_K_S.gguf b/QuantuMinx_4B.Q5_K_S.gguf new file mode 100644 index 0000000..93d6eda --- /dev/null +++ b/QuantuMinx_4B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0216a1dda90d30aff725301a48b5d9cceb3808cc0dd8ac17b2f20b62ccd1c7a3 +size 3163340000 diff --git a/QuantuMinx_4B.Q6_K.gguf b/QuantuMinx_4B.Q6_K.gguf new file mode 100644 index 0000000..8f5426c --- /dev/null +++ b/QuantuMinx_4B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61223625d800681377a3a11083357eee70403812998a7905d1dbf3ee22b5f9a6 +size 3710334176 diff --git a/QuantuMinx_4B.Q8_0.gguf b/QuantuMinx_4B.Q8_0.gguf new file mode 100644 index 0000000..e6a8720 --- /dev/null +++ b/QuantuMinx_4B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d516189e3971b40179f51117556538f700339b22b80e9c856970dbd07dcde162 +size 4803216608 diff --git a/QuantuMinx_4B.f16.gguf b/QuantuMinx_4B.f16.gguf new file mode 100644 index 0000000..7819e7b --- /dev/null +++ b/QuantuMinx_4B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5064d12bec16198949f0e56dfa4b5e5fa39cc95dcecf86466c30f20490d94245 +size 9033729248 diff --git a/README.md b/README.md new file mode 100644 index 0000000..495528a --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: FourOhFour/QuantuMinx_4B +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/FourOhFour/QuantuMinx_4B + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/QuantuMinx_4B-i1-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/QuantuMinx_4B-GGUF/resolve/main/QuantuMinx_4B.Q2_K.gguf) | Q2_K | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/QuantuMinx_4B-GGUF/resolve/main/QuantuMinx_4B.IQ3_XS.gguf) | IQ3_XS | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/QuantuMinx_4B-GGUF/resolve/main/QuantuMinx_4B.Q3_K_S.gguf) | Q3_K_S | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/QuantuMinx_4B-GGUF/resolve/main/QuantuMinx_4B.IQ3_S.gguf) | IQ3_S | 2.2 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/QuantuMinx_4B-GGUF/resolve/main/QuantuMinx_4B.IQ3_M.gguf) | IQ3_M | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/QuantuMinx_4B-GGUF/resolve/main/QuantuMinx_4B.Q3_K_M.gguf) | Q3_K_M | 2.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/QuantuMinx_4B-GGUF/resolve/main/QuantuMinx_4B.Q3_K_L.gguf) | Q3_K_L | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/QuantuMinx_4B-GGUF/resolve/main/QuantuMinx_4B.IQ4_XS.gguf) | IQ4_XS | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/QuantuMinx_4B-GGUF/resolve/main/QuantuMinx_4B.Q4_K_S.gguf) | Q4_K_S | 2.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/QuantuMinx_4B-GGUF/resolve/main/QuantuMinx_4B.Q4_K_M.gguf) | Q4_K_M | 2.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/QuantuMinx_4B-GGUF/resolve/main/QuantuMinx_4B.Q5_K_S.gguf) | Q5_K_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/QuantuMinx_4B-GGUF/resolve/main/QuantuMinx_4B.Q5_K_M.gguf) | Q5_K_M | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/QuantuMinx_4B-GGUF/resolve/main/QuantuMinx_4B.Q6_K.gguf) | Q6_K | 3.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/QuantuMinx_4B-GGUF/resolve/main/QuantuMinx_4B.Q8_0.gguf) | Q8_0 | 4.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/QuantuMinx_4B-GGUF/resolve/main/QuantuMinx_4B.f16.gguf) | f16 | 9.1 | 16 bpw, overkill | + +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. + +