commit 315bffaf09f291d7897fbf6b5070bcbefe342d0b Author: ModelHub XC Date: Sun Jul 19 10:32:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen-2.5-3B-Remix-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..413dfae --- /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 +Qwen-2.5-3B-Remix.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-2.5-3B-Remix.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-2.5-3B-Remix.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-2.5-3B-Remix.f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-2.5-3B-Remix.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-2.5-3B-Remix.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-2.5-3B-Remix.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-2.5-3B-Remix.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-2.5-3B-Remix.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-2.5-3B-Remix.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-2.5-3B-Remix.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-2.5-3B-Remix.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-2.5-3B-Remix.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-2.5-3B-Remix.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-2.5-3B-Remix.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen-2.5-3B-Remix.IQ3_M.gguf b/Qwen-2.5-3B-Remix.IQ3_M.gguf new file mode 100644 index 0000000..75145bc --- /dev/null +++ b/Qwen-2.5-3B-Remix.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e037d5fc76d5d6e0cf4a26ef58d352c12e4b050ed45825f248f48c364e8ab507 +size 1622599136 diff --git a/Qwen-2.5-3B-Remix.IQ3_S.gguf b/Qwen-2.5-3B-Remix.IQ3_S.gguf new file mode 100644 index 0000000..9ac8b37 --- /dev/null +++ b/Qwen-2.5-3B-Remix.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:033cbe7019fefdcc6864e48e0c7dd3fc00568885cac7aec9ab67b86a9eceb152 +size 1590568416 diff --git a/Qwen-2.5-3B-Remix.IQ3_XS.gguf b/Qwen-2.5-3B-Remix.IQ3_XS.gguf new file mode 100644 index 0000000..054e250 --- /dev/null +++ b/Qwen-2.5-3B-Remix.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f192ef49e09295d09f62e871d7dc6751863415228d03101d8467f159564db172 +size 1525540320 diff --git a/Qwen-2.5-3B-Remix.IQ4_XS.gguf b/Qwen-2.5-3B-Remix.IQ4_XS.gguf new file mode 100644 index 0000000..06187cc --- /dev/null +++ b/Qwen-2.5-3B-Remix.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ec833aafd779ca2dc62626e6f1de0358de34807f8415527c4062fb1b662f518 +size 1918492128 diff --git a/Qwen-2.5-3B-Remix.Q2_K.gguf b/Qwen-2.5-3B-Remix.Q2_K.gguf new file mode 100644 index 0000000..e109760 --- /dev/null +++ b/Qwen-2.5-3B-Remix.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09c15746e4d29f8319e01511c751827c3a7030da2de2c64f6dc01a2015160d24 +size 1376857568 diff --git a/Qwen-2.5-3B-Remix.Q3_K_L.gguf b/Qwen-2.5-3B-Remix.Q3_K_L.gguf new file mode 100644 index 0000000..acd4545 --- /dev/null +++ b/Qwen-2.5-3B-Remix.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf2495feddbe06705fc942dfd34b8f6834d902a80bee3bdfadaf6ce4bcebc7bd +size 1841096160 diff --git a/Qwen-2.5-3B-Remix.Q3_K_M.gguf b/Qwen-2.5-3B-Remix.Q3_K_M.gguf new file mode 100644 index 0000000..d56f3eb --- /dev/null +++ b/Qwen-2.5-3B-Remix.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c9cc17b7d9dc58a83b8fd32eefe0cbe6e5d5e49118bf5932052be2794dbc888 +size 1724179936 diff --git a/Qwen-2.5-3B-Remix.Q3_K_S.gguf b/Qwen-2.5-3B-Remix.Q3_K_S.gguf new file mode 100644 index 0000000..6cd993f --- /dev/null +++ b/Qwen-2.5-3B-Remix.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19831a863c36bf10072c6816509b5f229afbc98eedd687b5647ad7a7fba6b591 +size 1588061664 diff --git a/Qwen-2.5-3B-Remix.Q4_K_M.gguf b/Qwen-2.5-3B-Remix.Q4_K_M.gguf new file mode 100644 index 0000000..de9f713 --- /dev/null +++ b/Qwen-2.5-3B-Remix.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c9523a2d3bed235b1adadfea3bd9c453c1219baa54d0c5a7c3a4cf139c60c89 +size 2104933856 diff --git a/Qwen-2.5-3B-Remix.Q4_K_S.gguf b/Qwen-2.5-3B-Remix.Q4_K_S.gguf new file mode 100644 index 0000000..dddd597 --- /dev/null +++ b/Qwen-2.5-3B-Remix.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5bd860a80b3890459ff81ca03308e9db3ab82aeeae66d3be636029bbf2d3b5ba +size 2009415136 diff --git a/Qwen-2.5-3B-Remix.Q5_K_M.gguf b/Qwen-2.5-3B-Remix.Q5_K_M.gguf new file mode 100644 index 0000000..3bce732 --- /dev/null +++ b/Qwen-2.5-3B-Remix.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39dff4fe576366913b59a7dd43988f3b0010251ff42f491456ee605d1139f382 +size 2438741472 diff --git a/Qwen-2.5-3B-Remix.Q5_K_S.gguf b/Qwen-2.5-3B-Remix.Q5_K_S.gguf new file mode 100644 index 0000000..10d2ccc --- /dev/null +++ b/Qwen-2.5-3B-Remix.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b23649215a16ea602d7291b8d0fdeeecfc02418add2ab15156732742d943c7e7 +size 2383592928 diff --git a/Qwen-2.5-3B-Remix.Q6_K.gguf b/Qwen-2.5-3B-Remix.Q6_K.gguf new file mode 100644 index 0000000..b0360c9 --- /dev/null +++ b/Qwen-2.5-3B-Remix.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b80fbee16b439396a600f2afab4e6430e52cbf061cc0ee0aa1a7fa9f7083397 +size 2793412064 diff --git a/Qwen-2.5-3B-Remix.Q8_0.gguf b/Qwen-2.5-3B-Remix.Q8_0.gguf new file mode 100644 index 0000000..40b1140 --- /dev/null +++ b/Qwen-2.5-3B-Remix.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5c78f108146687c08ddda9d2a3bf7344c5e07667db1428c93b47beffb2e7cb6 +size 3616089568 diff --git a/Qwen-2.5-3B-Remix.f16.gguf b/Qwen-2.5-3B-Remix.f16.gguf new file mode 100644 index 0000000..0728acb --- /dev/null +++ b/Qwen-2.5-3B-Remix.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff185c7d01c34f020dd8552e035b479c9b30e05adf19e2c4c72abce4044feffb +size 6800647648 diff --git a/README.md b/README.md new file mode 100644 index 0000000..67760ac --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: bunnycore/Qwen-2.5-3B-Remix +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/bunnycore/Qwen-2.5-3B-Remix + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen-2.5-3B-Remix-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/Qwen-2.5-3B-Remix-GGUF/resolve/main/Qwen-2.5-3B-Remix.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-3B-Remix-GGUF/resolve/main/Qwen-2.5-3B-Remix.IQ3_XS.gguf) | IQ3_XS | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-3B-Remix-GGUF/resolve/main/Qwen-2.5-3B-Remix.Q3_K_S.gguf) | Q3_K_S | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-3B-Remix-GGUF/resolve/main/Qwen-2.5-3B-Remix.IQ3_S.gguf) | IQ3_S | 1.7 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-3B-Remix-GGUF/resolve/main/Qwen-2.5-3B-Remix.IQ3_M.gguf) | IQ3_M | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-3B-Remix-GGUF/resolve/main/Qwen-2.5-3B-Remix.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-3B-Remix-GGUF/resolve/main/Qwen-2.5-3B-Remix.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-3B-Remix-GGUF/resolve/main/Qwen-2.5-3B-Remix.IQ4_XS.gguf) | IQ4_XS | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-3B-Remix-GGUF/resolve/main/Qwen-2.5-3B-Remix.Q4_K_S.gguf) | Q4_K_S | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-3B-Remix-GGUF/resolve/main/Qwen-2.5-3B-Remix.Q4_K_M.gguf) | Q4_K_M | 2.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-3B-Remix-GGUF/resolve/main/Qwen-2.5-3B-Remix.Q5_K_S.gguf) | Q5_K_S | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-3B-Remix-GGUF/resolve/main/Qwen-2.5-3B-Remix.Q5_K_M.gguf) | Q5_K_M | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-3B-Remix-GGUF/resolve/main/Qwen-2.5-3B-Remix.Q6_K.gguf) | Q6_K | 2.9 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-3B-Remix-GGUF/resolve/main/Qwen-2.5-3B-Remix.Q8_0.gguf) | Q8_0 | 3.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-3B-Remix-GGUF/resolve/main/Qwen-2.5-3B-Remix.f16.gguf) | f16 | 6.9 | 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. + +