commit 4b7194b5912a1463944fdecde4bab72f9ece8251 Author: ModelHub XC Date: Wed Aug 5 05:45:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.2-1b-Mixer-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5c5e6a7 --- /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 +Llama-3.2-1b-Mixer.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1b-Mixer.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1b-Mixer.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1b-Mixer.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1b-Mixer.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1b-Mixer.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1b-Mixer.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1b-Mixer.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1b-Mixer.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1b-Mixer.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1b-Mixer.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1b-Mixer.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1b-Mixer.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1b-Mixer.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1b-Mixer.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.2-1b-Mixer.IQ3_M.gguf b/Llama-3.2-1b-Mixer.IQ3_M.gguf new file mode 100644 index 0000000..07fd7a7 --- /dev/null +++ b/Llama-3.2-1b-Mixer.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef2cdd5f2404bc35af1b28a936b17e0d538f520f23318e8cc9462e6bc0f5970d +size 770155296 diff --git a/Llama-3.2-1b-Mixer.IQ3_S.gguf b/Llama-3.2-1b-Mixer.IQ3_S.gguf new file mode 100644 index 0000000..d2e6d1e --- /dev/null +++ b/Llama-3.2-1b-Mixer.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf38bf125a0aa88b421d75d775bc4b224ecfb2ec4f2a4be5adae8272d816b9ef +size 756785952 diff --git a/Llama-3.2-1b-Mixer.IQ3_XS.gguf b/Llama-3.2-1b-Mixer.IQ3_XS.gguf new file mode 100644 index 0000000..7f5329c --- /dev/null +++ b/Llama-3.2-1b-Mixer.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71f9fb940344d0c67b73faf48a36017699a2bae52735b366f7fc40ff5144446c +size 733979424 diff --git a/Llama-3.2-1b-Mixer.IQ4_XS.gguf b/Llama-3.2-1b-Mixer.IQ4_XS.gguf new file mode 100644 index 0000000..fcdf7c0 --- /dev/null +++ b/Llama-3.2-1b-Mixer.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e289bf4d5265a826d5efeb173579d42afd792171a4cb2a4750a516729be65357 +size 887927584 diff --git a/Llama-3.2-1b-Mixer.Q2_K.gguf b/Llama-3.2-1b-Mixer.Q2_K.gguf new file mode 100644 index 0000000..46f26be --- /dev/null +++ b/Llama-3.2-1b-Mixer.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c40352173d2b4013ccd89aa0784d805b4339784ac9ccd8bbf204fb7d1bf1924 +size 667063072 diff --git a/Llama-3.2-1b-Mixer.Q3_K_L.gguf b/Llama-3.2-1b-Mixer.Q3_K_L.gguf new file mode 100644 index 0000000..e907bab --- /dev/null +++ b/Llama-3.2-1b-Mixer.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7bfdb1053d8bf040d56a6d3fb8a19aaf4d10703dc3fa9a6884a5c58787141c96 +size 845390624 diff --git a/Llama-3.2-1b-Mixer.Q3_K_M.gguf b/Llama-3.2-1b-Mixer.Q3_K_M.gguf new file mode 100644 index 0000000..09fd8c2 --- /dev/null +++ b/Llama-3.2-1b-Mixer.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4229cde189a82424cb9972bb68e3e39b9bd9dd68c7d5da25bb5ad189c0e5b552 +size 803709728 diff --git a/Llama-3.2-1b-Mixer.Q3_K_S.gguf b/Llama-3.2-1b-Mixer.Q3_K_S.gguf new file mode 100644 index 0000000..2a518a9 --- /dev/null +++ b/Llama-3.2-1b-Mixer.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf27cf62c0a5338f721e64840f7708da2ea76480888c9919987291a7a9dd3779 +size 754557728 diff --git a/Llama-3.2-1b-Mixer.Q4_K_M.gguf b/Llama-3.2-1b-Mixer.Q4_K_M.gguf new file mode 100644 index 0000000..0a6f021 --- /dev/null +++ b/Llama-3.2-1b-Mixer.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05e6a111ca07ea648e4d73655869c09b9187831debf0a2a901919506aff9bd3a +size 955446048 diff --git a/Llama-3.2-1b-Mixer.Q4_K_S.gguf b/Llama-3.2-1b-Mixer.Q4_K_S.gguf new file mode 100644 index 0000000..cb24bc5 --- /dev/null +++ b/Llama-3.2-1b-Mixer.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7106885bd236a2c762146c532d00226d0fc7fb3be48905e6896b3619dd97e564 +size 923398944 diff --git a/Llama-3.2-1b-Mixer.Q5_K_M.gguf b/Llama-3.2-1b-Mixer.Q5_K_M.gguf new file mode 100644 index 0000000..da4dc8b --- /dev/null +++ b/Llama-3.2-1b-Mixer.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31f2c8939a0f717e468a1f9572c0c40bc918bb4d501d57cb89d50b08ac2af623 +size 1092088608 diff --git a/Llama-3.2-1b-Mixer.Q5_K_S.gguf b/Llama-3.2-1b-Mixer.Q5_K_S.gguf new file mode 100644 index 0000000..92d0b4b --- /dev/null +++ b/Llama-3.2-1b-Mixer.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ce7c966678402cc2b19bfffbb3c2fd97d0f30dd62d9a1d93040ea35f4e142ad +size 1073148704 diff --git a/Llama-3.2-1b-Mixer.Q6_K.gguf b/Llama-3.2-1b-Mixer.Q6_K.gguf new file mode 100644 index 0000000..eabb4c4 --- /dev/null +++ b/Llama-3.2-1b-Mixer.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48f9454e6d9d1f27af1c569e68e4999a558fec91118f60db71d02ff0818ed85c +size 1237271328 diff --git a/Llama-3.2-1b-Mixer.Q8_0.gguf b/Llama-3.2-1b-Mixer.Q8_0.gguf new file mode 100644 index 0000000..c69422e --- /dev/null +++ b/Llama-3.2-1b-Mixer.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae16bccf376148e0171f758e35384bf1fcb954c0f787a57911709f5f4720e056 +size 1600168736 diff --git a/Llama-3.2-1b-Mixer.f16.gguf b/Llama-3.2-1b-Mixer.f16.gguf new file mode 100644 index 0000000..17e660b --- /dev/null +++ b/Llama-3.2-1b-Mixer.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de24a4c32d42f0a1cb147cbedae5db2fa4e13b5718a10b06bb7d7b91955e13d4 +size 3004932896 diff --git a/README.md b/README.md new file mode 100644 index 0000000..54d8944 --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: bunnycore/Llama-3.2-1b-Mixer +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/bunnycore/Llama-3.2-1b-Mixer + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-3.2-1b-Mixer-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-3.2-1b-Mixer-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-Mixer-GGUF/resolve/main/Llama-3.2-1b-Mixer.Q2_K.gguf) | Q2_K | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1b-Mixer-GGUF/resolve/main/Llama-3.2-1b-Mixer.IQ3_XS.gguf) | IQ3_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1b-Mixer-GGUF/resolve/main/Llama-3.2-1b-Mixer.Q3_K_S.gguf) | Q3_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1b-Mixer-GGUF/resolve/main/Llama-3.2-1b-Mixer.IQ3_S.gguf) | IQ3_S | 0.9 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1b-Mixer-GGUF/resolve/main/Llama-3.2-1b-Mixer.IQ3_M.gguf) | IQ3_M | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1b-Mixer-GGUF/resolve/main/Llama-3.2-1b-Mixer.Q3_K_M.gguf) | Q3_K_M | 0.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1b-Mixer-GGUF/resolve/main/Llama-3.2-1b-Mixer.Q3_K_L.gguf) | Q3_K_L | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1b-Mixer-GGUF/resolve/main/Llama-3.2-1b-Mixer.IQ4_XS.gguf) | IQ4_XS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1b-Mixer-GGUF/resolve/main/Llama-3.2-1b-Mixer.Q4_K_S.gguf) | Q4_K_S | 1.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1b-Mixer-GGUF/resolve/main/Llama-3.2-1b-Mixer.Q4_K_M.gguf) | Q4_K_M | 1.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1b-Mixer-GGUF/resolve/main/Llama-3.2-1b-Mixer.Q5_K_S.gguf) | Q5_K_S | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1b-Mixer-GGUF/resolve/main/Llama-3.2-1b-Mixer.Q5_K_M.gguf) | Q5_K_M | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1b-Mixer-GGUF/resolve/main/Llama-3.2-1b-Mixer.Q6_K.gguf) | Q6_K | 1.3 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1b-Mixer-GGUF/resolve/main/Llama-3.2-1b-Mixer.Q8_0.gguf) | Q8_0 | 1.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1b-Mixer-GGUF/resolve/main/Llama-3.2-1b-Mixer.f16.gguf) | f16 | 3.1 | 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. + +