commit feb5b0d8f33ac7e95660df980f6d648424db8de6 Author: ModelHub XC Date: Thu Oct 22 14:46:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.2-1B-4B-Quad-MoE-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..86da16c --- /dev/null +++ b/.gitattributes @@ -0,0 +1,47 @@ +*.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 +Llama-3.2-1B-4B-Quad-MoE.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-4B-Quad-MoE.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-4B-Quad-MoE.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-4B-Quad-MoE.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-4B-Quad-MoE.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-4B-Quad-MoE.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-4B-Quad-MoE.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-4B-Quad-MoE.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-4B-Quad-MoE.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-4B-Quad-MoE.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-4B-Quad-MoE.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-4B-Quad-MoE.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.2-1B-4B-Quad-MoE.IQ4_XS.gguf b/Llama-3.2-1B-4B-Quad-MoE.IQ4_XS.gguf new file mode 100644 index 0000000..b2009c8 --- /dev/null +++ b/Llama-3.2-1B-4B-Quad-MoE.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9dae9d671ec99f1379124523dae13a5ba3054fa828efeab60febeedf35f7a9a3 +size 2048097312 diff --git a/Llama-3.2-1B-4B-Quad-MoE.Q2_K.gguf b/Llama-3.2-1B-4B-Quad-MoE.Q2_K.gguf new file mode 100644 index 0000000..a17a620 --- /dev/null +++ b/Llama-3.2-1B-4B-Quad-MoE.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0dfc7c2141fed8c5c7b856ef129924df5758ed8036875e97eed0c6240eb27bee +size 1455914016 diff --git a/Llama-3.2-1B-4B-Quad-MoE.Q3_K_L.gguf b/Llama-3.2-1B-4B-Quad-MoE.Q3_K_L.gguf new file mode 100644 index 0000000..5724b76 --- /dev/null +++ b/Llama-3.2-1B-4B-Quad-MoE.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04a0c13ef47bd661cb396f5786c3c34c84d63c305de52d3189adf59da0f09b00 +size 1978760224 diff --git a/Llama-3.2-1B-4B-Quad-MoE.Q3_K_M.gguf b/Llama-3.2-1B-4B-Quad-MoE.Q3_K_M.gguf new file mode 100644 index 0000000..21654cb --- /dev/null +++ b/Llama-3.2-1B-4B-Quad-MoE.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:536eb14853ae8a4c8b8497733faf124667394343648e0d0b813e06aeec3c29b4 +size 1842707488 diff --git a/Llama-3.2-1B-4B-Quad-MoE.Q3_K_S.gguf b/Llama-3.2-1B-4B-Quad-MoE.Q3_K_S.gguf new file mode 100644 index 0000000..54ca3b1 --- /dev/null +++ b/Llama-3.2-1B-4B-Quad-MoE.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e04f3f4f302c8a799ce897f086b938f8486ab1faa07cc0e2a6712f8baf71a62 +size 1680309280 diff --git a/Llama-3.2-1B-4B-Quad-MoE.Q4_K_M.gguf b/Llama-3.2-1B-4B-Quad-MoE.Q4_K_M.gguf new file mode 100644 index 0000000..b5cd680 --- /dev/null +++ b/Llama-3.2-1B-4B-Quad-MoE.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fed835c2c3ee921daec10add29528176b94c91e6983ebcb3b4dfaff3d38c96f +size 2270985248 diff --git a/Llama-3.2-1B-4B-Quad-MoE.Q4_K_S.gguf b/Llama-3.2-1B-4B-Quad-MoE.Q4_K_S.gguf new file mode 100644 index 0000000..5873706 --- /dev/null +++ b/Llama-3.2-1B-4B-Quad-MoE.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c756cffe8d5c078c7f237f44264abbcece6c32405825a1d011259d237cc035d +size 2147712032 diff --git a/Llama-3.2-1B-4B-Quad-MoE.Q5_K_M.gguf b/Llama-3.2-1B-4B-Quad-MoE.Q5_K_M.gguf new file mode 100644 index 0000000..9f61d38 --- /dev/null +++ b/Llama-3.2-1B-4B-Quad-MoE.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:890be8f383ea28451ec39307b5fefde318e20586e3c34598f3aa6682633cd8e3 +size 2626452512 diff --git a/Llama-3.2-1B-4B-Quad-MoE.Q5_K_S.gguf b/Llama-3.2-1B-4B-Quad-MoE.Q5_K_S.gguf new file mode 100644 index 0000000..8f1edc1 --- /dev/null +++ b/Llama-3.2-1B-4B-Quad-MoE.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5940d797387873fbe9075198d0880eeea21e50f552b5160faa2f93e29805d787 +size 2554035232 diff --git a/Llama-3.2-1B-4B-Quad-MoE.Q6_K.gguf b/Llama-3.2-1B-4B-Quad-MoE.Q6_K.gguf new file mode 100644 index 0000000..ed2ec37 --- /dev/null +++ b/Llama-3.2-1B-4B-Quad-MoE.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7de676257885edddacc1590db3730c38458cf470f913aa7a66d8480e3a531a7b +size 3004136480 diff --git a/Llama-3.2-1B-4B-Quad-MoE.Q8_0.gguf b/Llama-3.2-1B-4B-Quad-MoE.Q8_0.gguf new file mode 100644 index 0000000..31c3fe4 --- /dev/null +++ b/Llama-3.2-1B-4B-Quad-MoE.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed4e281f72fddd932070fb6fa25813fbf6ed1e21a7d23b0a3dfbdd4fff6bc978 +size 3888524320 diff --git a/Llama-3.2-1B-4B-Quad-MoE.f16.gguf b/Llama-3.2-1B-4B-Quad-MoE.f16.gguf new file mode 100644 index 0000000..23ab5f1 --- /dev/null +++ b/Llama-3.2-1B-4B-Quad-MoE.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1b27243ca2bf4d299fb685d33bf0125e1b040378ea8e7981808fbb1f8cb0725 +size 7311961120 diff --git a/README.md b/README.md new file mode 100644 index 0000000..66b16a0 --- /dev/null +++ b/README.md @@ -0,0 +1,80 @@ +--- +base_model: Fu01978/Llama-3.2-1B-4B-Quad-MoE +language: +- en +library_name: transformers +license: llama3.2 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- mixture-of-experts +- moe +- 4-experts +- merge +- mergekit +- llama +- llama3.2 +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Fu01978/Llama-3.2-1B-4B-Quad-MoE + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-3.2-1B-4B-Quad-MoE-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-3.2-1B-4B-Quad-MoE-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/Llama-3.2-1B-4B-Quad-MoE-GGUF/resolve/main/Llama-3.2-1B-4B-Quad-MoE.Q2_K.gguf) | Q2_K | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-4B-Quad-MoE-GGUF/resolve/main/Llama-3.2-1B-4B-Quad-MoE.Q3_K_S.gguf) | Q3_K_S | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-4B-Quad-MoE-GGUF/resolve/main/Llama-3.2-1B-4B-Quad-MoE.Q3_K_M.gguf) | Q3_K_M | 1.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-4B-Quad-MoE-GGUF/resolve/main/Llama-3.2-1B-4B-Quad-MoE.Q3_K_L.gguf) | Q3_K_L | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-4B-Quad-MoE-GGUF/resolve/main/Llama-3.2-1B-4B-Quad-MoE.IQ4_XS.gguf) | IQ4_XS | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-4B-Quad-MoE-GGUF/resolve/main/Llama-3.2-1B-4B-Quad-MoE.Q4_K_S.gguf) | Q4_K_S | 2.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-4B-Quad-MoE-GGUF/resolve/main/Llama-3.2-1B-4B-Quad-MoE.Q4_K_M.gguf) | Q4_K_M | 2.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-4B-Quad-MoE-GGUF/resolve/main/Llama-3.2-1B-4B-Quad-MoE.Q5_K_S.gguf) | Q5_K_S | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-4B-Quad-MoE-GGUF/resolve/main/Llama-3.2-1B-4B-Quad-MoE.Q5_K_M.gguf) | Q5_K_M | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-4B-Quad-MoE-GGUF/resolve/main/Llama-3.2-1B-4B-Quad-MoE.Q6_K.gguf) | Q6_K | 3.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-4B-Quad-MoE-GGUF/resolve/main/Llama-3.2-1B-4B-Quad-MoE.Q8_0.gguf) | Q8_0 | 4.0 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-4B-Quad-MoE-GGUF/resolve/main/Llama-3.2-1B-4B-Quad-MoE.f16.gguf) | f16 | 7.4 | 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. + +