commit 950f2202c3c0ae413aca8c81aaffe3fd5452a885 Author: ModelHub XC Date: Sat Aug 1 12:44:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-4B-Thinking-2507-Gemini-2.5-Pro-Distill-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2c64d94 --- /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 +Qwen3-4B-Thinking-2507-Gemini-2.5-Pro-Distill.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Thinking-2507-Gemini-2.5-Pro-Distill.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Thinking-2507-Gemini-2.5-Pro-Distill.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Thinking-2507-Gemini-2.5-Pro-Distill.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Thinking-2507-Gemini-2.5-Pro-Distill.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Thinking-2507-Gemini-2.5-Pro-Distill.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Thinking-2507-Gemini-2.5-Pro-Distill.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Thinking-2507-Gemini-2.5-Pro-Distill.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Thinking-2507-Gemini-2.5-Pro-Distill.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Thinking-2507-Gemini-2.5-Pro-Distill.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Thinking-2507-Gemini-2.5-Pro-Distill.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Thinking-2507-Gemini-2.5-Pro-Distill.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-4B-Thinking-2507-Gemini-2.5-Pro-Distill.IQ4_XS.gguf b/Qwen3-4B-Thinking-2507-Gemini-2.5-Pro-Distill.IQ4_XS.gguf new file mode 100644 index 0000000..635ff2d --- /dev/null +++ b/Qwen3-4B-Thinking-2507-Gemini-2.5-Pro-Distill.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd92f9ccbe17371af5cade619f9bf4e60def379f96d5efdaff27efa5a039f365 +size 2286316256 diff --git a/Qwen3-4B-Thinking-2507-Gemini-2.5-Pro-Distill.Q2_K.gguf b/Qwen3-4B-Thinking-2507-Gemini-2.5-Pro-Distill.Q2_K.gguf new file mode 100644 index 0000000..9b38363 --- /dev/null +++ b/Qwen3-4B-Thinking-2507-Gemini-2.5-Pro-Distill.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4db13be310104c15b5b82cd1b2dbe4d96ca8cef891a77a4302250959ea7d3422 +size 1669499616 diff --git a/Qwen3-4B-Thinking-2507-Gemini-2.5-Pro-Distill.Q3_K_L.gguf b/Qwen3-4B-Thinking-2507-Gemini-2.5-Pro-Distill.Q3_K_L.gguf new file mode 100644 index 0000000..eaa6ca3 --- /dev/null +++ b/Qwen3-4B-Thinking-2507-Gemini-2.5-Pro-Distill.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbf601c4e392082ab7fc67f1295d19ad0a19027cbc112d3bf20d02552d5cb61b +size 2239785696 diff --git a/Qwen3-4B-Thinking-2507-Gemini-2.5-Pro-Distill.Q3_K_M.gguf b/Qwen3-4B-Thinking-2507-Gemini-2.5-Pro-Distill.Q3_K_M.gguf new file mode 100644 index 0000000..7b2b64c --- /dev/null +++ b/Qwen3-4B-Thinking-2507-Gemini-2.5-Pro-Distill.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ea6baedd3f532394d47888f826fafd4c5bf59c11ed3d7e37615f66b72654ac8 +size 2075618016 diff --git a/Qwen3-4B-Thinking-2507-Gemini-2.5-Pro-Distill.Q3_K_S.gguf b/Qwen3-4B-Thinking-2507-Gemini-2.5-Pro-Distill.Q3_K_S.gguf new file mode 100644 index 0000000..132680a --- /dev/null +++ b/Qwen3-4B-Thinking-2507-Gemini-2.5-Pro-Distill.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c82c9988a2f9bfa3594029958d82b15967602cad7fc875dd078d616411ece285 +size 1886997216 diff --git a/Qwen3-4B-Thinking-2507-Gemini-2.5-Pro-Distill.Q4_K_M.gguf b/Qwen3-4B-Thinking-2507-Gemini-2.5-Pro-Distill.Q4_K_M.gguf new file mode 100644 index 0000000..63107a0 --- /dev/null +++ b/Qwen3-4B-Thinking-2507-Gemini-2.5-Pro-Distill.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45a0d0466720691df532d09ffb25ced6656712ba88a195ddbfae331b5113f05c +size 2497280736 diff --git a/Qwen3-4B-Thinking-2507-Gemini-2.5-Pro-Distill.Q4_K_S.gguf b/Qwen3-4B-Thinking-2507-Gemini-2.5-Pro-Distill.Q4_K_S.gguf new file mode 100644 index 0000000..e53e027 --- /dev/null +++ b/Qwen3-4B-Thinking-2507-Gemini-2.5-Pro-Distill.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0dce37e0895a81c9b3226a24df0034424afde837cd7a8b02b9b0ce442b6c5a8 +size 2383309536 diff --git a/Qwen3-4B-Thinking-2507-Gemini-2.5-Pro-Distill.Q5_K_M.gguf b/Qwen3-4B-Thinking-2507-Gemini-2.5-Pro-Distill.Q5_K_M.gguf new file mode 100644 index 0000000..aa20e57 --- /dev/null +++ b/Qwen3-4B-Thinking-2507-Gemini-2.5-Pro-Distill.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a70e84d61e5693576855952e4d64b3a649e1d681882ed59d6402a85c3328a2c8 +size 2889513696 diff --git a/Qwen3-4B-Thinking-2507-Gemini-2.5-Pro-Distill.Q5_K_S.gguf b/Qwen3-4B-Thinking-2507-Gemini-2.5-Pro-Distill.Q5_K_S.gguf new file mode 100644 index 0000000..becc540 --- /dev/null +++ b/Qwen3-4B-Thinking-2507-Gemini-2.5-Pro-Distill.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:986a8e36daf6e757cb35b1844268c83c68357eb798549b1d3359613a9895cc3c +size 2823711456 diff --git a/Qwen3-4B-Thinking-2507-Gemini-2.5-Pro-Distill.Q6_K.gguf b/Qwen3-4B-Thinking-2507-Gemini-2.5-Pro-Distill.Q6_K.gguf new file mode 100644 index 0000000..3e9ba24 --- /dev/null +++ b/Qwen3-4B-Thinking-2507-Gemini-2.5-Pro-Distill.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:661cc304a80a20d603c92b437e0162d9e6cbaf7e7237355bdc443c91833672a1 +size 3306261216 diff --git a/Qwen3-4B-Thinking-2507-Gemini-2.5-Pro-Distill.Q8_0.gguf b/Qwen3-4B-Thinking-2507-Gemini-2.5-Pro-Distill.Q8_0.gguf new file mode 100644 index 0000000..2691425 --- /dev/null +++ b/Qwen3-4B-Thinking-2507-Gemini-2.5-Pro-Distill.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d73aa4f3069b0826350e2600136c9433adb4fb1416ff973540bc9ebcfa3592aa +size 4280405216 diff --git a/Qwen3-4B-Thinking-2507-Gemini-2.5-Pro-Distill.f16.gguf b/Qwen3-4B-Thinking-2507-Gemini-2.5-Pro-Distill.f16.gguf new file mode 100644 index 0000000..d836a4b --- /dev/null +++ b/Qwen3-4B-Thinking-2507-Gemini-2.5-Pro-Distill.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a483c33548c19458472a0dbe59eaee30f93b52e6173af43ceb92adbbfa93def +size 8051285216 diff --git a/README.md b/README.md new file mode 100644 index 0000000..d33de19 --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: Liontix/Qwen3-4B-Thinking-2507-Gemini-2.5-Pro-Distill +datasets: +- Liontix/gemini-2.5-pro-200x +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Liontix/Qwen3-4B-Thinking-2507-Gemini-2.5-Pro-Distill + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-4B-Thinking-2507-Gemini-2.5-Pro-Distill-GGUF).*** + +weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. +## 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/Qwen3-4B-Thinking-2507-Gemini-2.5-Pro-Distill-GGUF/resolve/main/Qwen3-4B-Thinking-2507-Gemini-2.5-Pro-Distill.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-Gemini-2.5-Pro-Distill-GGUF/resolve/main/Qwen3-4B-Thinking-2507-Gemini-2.5-Pro-Distill.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-Gemini-2.5-Pro-Distill-GGUF/resolve/main/Qwen3-4B-Thinking-2507-Gemini-2.5-Pro-Distill.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-Gemini-2.5-Pro-Distill-GGUF/resolve/main/Qwen3-4B-Thinking-2507-Gemini-2.5-Pro-Distill.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-Gemini-2.5-Pro-Distill-GGUF/resolve/main/Qwen3-4B-Thinking-2507-Gemini-2.5-Pro-Distill.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-Gemini-2.5-Pro-Distill-GGUF/resolve/main/Qwen3-4B-Thinking-2507-Gemini-2.5-Pro-Distill.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-Gemini-2.5-Pro-Distill-GGUF/resolve/main/Qwen3-4B-Thinking-2507-Gemini-2.5-Pro-Distill.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-Gemini-2.5-Pro-Distill-GGUF/resolve/main/Qwen3-4B-Thinking-2507-Gemini-2.5-Pro-Distill.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-Gemini-2.5-Pro-Distill-GGUF/resolve/main/Qwen3-4B-Thinking-2507-Gemini-2.5-Pro-Distill.Q5_K_M.gguf) | Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-Gemini-2.5-Pro-Distill-GGUF/resolve/main/Qwen3-4B-Thinking-2507-Gemini-2.5-Pro-Distill.Q6_K.gguf) | Q6_K | 3.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-Gemini-2.5-Pro-Distill-GGUF/resolve/main/Qwen3-4B-Thinking-2507-Gemini-2.5-Pro-Distill.Q8_0.gguf) | Q8_0 | 4.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-Gemini-2.5-Pro-Distill-GGUF/resolve/main/Qwen3-4B-Thinking-2507-Gemini-2.5-Pro-Distill.f16.gguf) | f16 | 8.2 | 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. + +