commit 6b6c3c81e62944b7d76c2e1e2f9e9884321343e3 Author: ModelHub XC Date: Fri Oct 23 08:27:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Q3-ColdBrew-5B_MOE-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..4e8e999 --- /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 +Q3-ColdBrew-5B_MOE.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Q3-ColdBrew-5B_MOE.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Q3-ColdBrew-5B_MOE.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Q3-ColdBrew-5B_MOE.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Q3-ColdBrew-5B_MOE.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Q3-ColdBrew-5B_MOE.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Q3-ColdBrew-5B_MOE.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Q3-ColdBrew-5B_MOE.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Q3-ColdBrew-5B_MOE.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Q3-ColdBrew-5B_MOE.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Q3-ColdBrew-5B_MOE.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Q3-ColdBrew-5B_MOE.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Q3-ColdBrew-5B_MOE.IQ4_XS.gguf b/Q3-ColdBrew-5B_MOE.IQ4_XS.gguf new file mode 100644 index 0000000..afed965 --- /dev/null +++ b/Q3-ColdBrew-5B_MOE.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1eecfbf09a1a8f25ee91f1801c8865fa9961ccf3098fb37bd9de235d5ffd127c +size 2719434368 diff --git a/Q3-ColdBrew-5B_MOE.Q2_K.gguf b/Q3-ColdBrew-5B_MOE.Q2_K.gguf new file mode 100644 index 0000000..1e1be60 --- /dev/null +++ b/Q3-ColdBrew-5B_MOE.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7373c78e09525261264462aad8a06c64288ddc5637463b240c9500bc310509c2 +size 1926514304 diff --git a/Q3-ColdBrew-5B_MOE.Q3_K_L.gguf b/Q3-ColdBrew-5B_MOE.Q3_K_L.gguf new file mode 100644 index 0000000..ea572b0 --- /dev/null +++ b/Q3-ColdBrew-5B_MOE.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6cd10d5e85bbcdb1f4dcff39cc65356decd011d7425907f4ad2c9ed988fd228 +size 2639414912 diff --git a/Q3-ColdBrew-5B_MOE.Q3_K_M.gguf b/Q3-ColdBrew-5B_MOE.Q3_K_M.gguf new file mode 100644 index 0000000..1c32457 --- /dev/null +++ b/Q3-ColdBrew-5B_MOE.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f44d8c64b5cb82a7bc230ee9d9a26768ba62c8847e3f3c4b5010afed131abb6a +size 2448049792 diff --git a/Q3-ColdBrew-5B_MOE.Q3_K_S.gguf b/Q3-ColdBrew-5B_MOE.Q3_K_S.gguf new file mode 100644 index 0000000..86825f0 --- /dev/null +++ b/Q3-ColdBrew-5B_MOE.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a46c3e436a5d7bd07e9a70411a57574d7396d6dfe090262d6c133696f1a72b5 +size 2230666880 diff --git a/Q3-ColdBrew-5B_MOE.Q4_K_M.gguf b/Q3-ColdBrew-5B_MOE.Q4_K_M.gguf new file mode 100644 index 0000000..5ac4254 --- /dev/null +++ b/Q3-ColdBrew-5B_MOE.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9863b55db78ba153316cbc1b38f6f718beb2411cf7cc234e8da282af84da6101 +size 3028207232 diff --git a/Q3-ColdBrew-5B_MOE.Q4_K_S.gguf b/Q3-ColdBrew-5B_MOE.Q4_K_S.gguf new file mode 100644 index 0000000..045aae9 --- /dev/null +++ b/Q3-ColdBrew-5B_MOE.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84a9f762ad6f72dc83176d6acf4a377e0a154ac20362b14d26be39266beda04b +size 2858894976 diff --git a/Q3-ColdBrew-5B_MOE.Q5_K_M.gguf b/Q3-ColdBrew-5B_MOE.Q5_K_M.gguf new file mode 100644 index 0000000..58d506b --- /dev/null +++ b/Q3-ColdBrew-5B_MOE.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6757356b4b37ba45ff94d35e0baab5c083a66530de6851cdb5acd3c632415e94 +size 3508979328 diff --git a/Q3-ColdBrew-5B_MOE.Q5_K_S.gguf b/Q3-ColdBrew-5B_MOE.Q5_K_S.gguf new file mode 100644 index 0000000..29a658c --- /dev/null +++ b/Q3-ColdBrew-5B_MOE.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20ca3567f0190f032fe285a7adbdb7e937c3775b8be85291a9b31ef853d1749d +size 3411494528 diff --git a/Q3-ColdBrew-5B_MOE.Q6_K.gguf b/Q3-ColdBrew-5B_MOE.Q6_K.gguf new file mode 100644 index 0000000..0096a97 --- /dev/null +++ b/Q3-ColdBrew-5B_MOE.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da791cac8229b6096c145ef19f8b79e5e60750f1d67fa9e2a1a66c277422d321 +size 4019799680 diff --git a/Q3-ColdBrew-5B_MOE.Q8_0.gguf b/Q3-ColdBrew-5B_MOE.Q8_0.gguf new file mode 100644 index 0000000..f94408b --- /dev/null +++ b/Q3-ColdBrew-5B_MOE.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2fc16ae6c22950f50af896cc4851cc58ef376f487071ab4a9345363c0a8fd28 +size 5204422272 diff --git a/Q3-ColdBrew-5B_MOE.f16.gguf b/Q3-ColdBrew-5B_MOE.f16.gguf new file mode 100644 index 0000000..0481c10 --- /dev/null +++ b/Q3-ColdBrew-5B_MOE.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02f5c4dd26122f9f4e3af87e7aa49f28aa69a7739096e5f1eb93a0dcb92c3daa +size 9790058112 diff --git a/README.md b/README.md new file mode 100644 index 0000000..7e2d812 --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: SvalTek/Q3-ColdBrew-5B_MOE +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- qwen3_moe +--- +## About + + + + + + + + + +static quants of https://huggingface.co/SvalTek/Q3-ColdBrew-5B_MOE + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Q3-ColdBrew-5B_MOE-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Q3-ColdBrew-5B_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/Q3-ColdBrew-5B_MOE-GGUF/resolve/main/Q3-ColdBrew-5B_MOE.Q2_K.gguf) | Q2_K | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Q3-ColdBrew-5B_MOE-GGUF/resolve/main/Q3-ColdBrew-5B_MOE.Q3_K_S.gguf) | Q3_K_S | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Q3-ColdBrew-5B_MOE-GGUF/resolve/main/Q3-ColdBrew-5B_MOE.Q3_K_M.gguf) | Q3_K_M | 2.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Q3-ColdBrew-5B_MOE-GGUF/resolve/main/Q3-ColdBrew-5B_MOE.Q3_K_L.gguf) | Q3_K_L | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Q3-ColdBrew-5B_MOE-GGUF/resolve/main/Q3-ColdBrew-5B_MOE.IQ4_XS.gguf) | IQ4_XS | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/Q3-ColdBrew-5B_MOE-GGUF/resolve/main/Q3-ColdBrew-5B_MOE.Q4_K_S.gguf) | Q4_K_S | 3.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Q3-ColdBrew-5B_MOE-GGUF/resolve/main/Q3-ColdBrew-5B_MOE.Q4_K_M.gguf) | Q4_K_M | 3.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Q3-ColdBrew-5B_MOE-GGUF/resolve/main/Q3-ColdBrew-5B_MOE.Q5_K_S.gguf) | Q5_K_S | 3.5 | | +| [GGUF](https://huggingface.co/mradermacher/Q3-ColdBrew-5B_MOE-GGUF/resolve/main/Q3-ColdBrew-5B_MOE.Q5_K_M.gguf) | Q5_K_M | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Q3-ColdBrew-5B_MOE-GGUF/resolve/main/Q3-ColdBrew-5B_MOE.Q6_K.gguf) | Q6_K | 4.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Q3-ColdBrew-5B_MOE-GGUF/resolve/main/Q3-ColdBrew-5B_MOE.Q8_0.gguf) | Q8_0 | 5.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Q3-ColdBrew-5B_MOE-GGUF/resolve/main/Q3-ColdBrew-5B_MOE.f16.gguf) | f16 | 9.9 | 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. + +