commit 70cfc3473b3856e78829f8048c51bc63ac7a306c Author: ModelHub XC Date: Thu Jul 23 08:52:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-4B-Thinking-2507-Genius-Buddy-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5bd96b3 --- /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-Genius-Buddy.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Thinking-2507-Genius-Buddy.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Thinking-2507-Genius-Buddy.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Thinking-2507-Genius-Buddy.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Thinking-2507-Genius-Buddy.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Thinking-2507-Genius-Buddy.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Thinking-2507-Genius-Buddy.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Thinking-2507-Genius-Buddy.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Thinking-2507-Genius-Buddy.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Thinking-2507-Genius-Buddy.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Thinking-2507-Genius-Buddy.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Thinking-2507-Genius-Buddy.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-4B-Thinking-2507-Genius-Buddy.IQ4_XS.gguf b/Qwen3-4B-Thinking-2507-Genius-Buddy.IQ4_XS.gguf new file mode 100644 index 0000000..2eb030f --- /dev/null +++ b/Qwen3-4B-Thinking-2507-Genius-Buddy.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0329a870384f4a7a0273b4131a858c6754520346990103884af7dd2d344253b +size 2492949824 diff --git a/Qwen3-4B-Thinking-2507-Genius-Buddy.Q2_K.gguf b/Qwen3-4B-Thinking-2507-Genius-Buddy.Q2_K.gguf new file mode 100644 index 0000000..6fe223b --- /dev/null +++ b/Qwen3-4B-Thinking-2507-Genius-Buddy.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8b798565c6806b65a6b9c69dbf8b752fc9920840a35ec7c3a76bf35493eb810 +size 1797126464 diff --git a/Qwen3-4B-Thinking-2507-Genius-Buddy.Q3_K_L.gguf b/Qwen3-4B-Thinking-2507-Genius-Buddy.Q3_K_L.gguf new file mode 100644 index 0000000..369a29b --- /dev/null +++ b/Qwen3-4B-Thinking-2507-Genius-Buddy.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:996f90a4a5897bfcb09c80ae6531403ac57916fcca526e8c4abc1c317ac30c43 +size 2406915904 diff --git a/Qwen3-4B-Thinking-2507-Genius-Buddy.Q3_K_M.gguf b/Qwen3-4B-Thinking-2507-Genius-Buddy.Q3_K_M.gguf new file mode 100644 index 0000000..f3f7403 --- /dev/null +++ b/Qwen3-4B-Thinking-2507-Genius-Buddy.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0211b2693bf049994fe39bb97176ffdc7cc97614b500f50ec21ef8bf728854c5 +size 2242748224 diff --git a/Qwen3-4B-Thinking-2507-Genius-Buddy.Q3_K_S.gguf b/Qwen3-4B-Thinking-2507-Genius-Buddy.Q3_K_S.gguf new file mode 100644 index 0000000..2772ce9 --- /dev/null +++ b/Qwen3-4B-Thinking-2507-Genius-Buddy.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dcfb08309002dab0e856cc8916a09d6aa12e4fd5b1eedfef2a990258db79764d +size 2054127424 diff --git a/Qwen3-4B-Thinking-2507-Genius-Buddy.Q4_K_M.gguf b/Qwen3-4B-Thinking-2507-Genius-Buddy.Q4_K_M.gguf new file mode 100644 index 0000000..73418ca --- /dev/null +++ b/Qwen3-4B-Thinking-2507-Genius-Buddy.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af26c3012333016bcb169c8a0dcca31618aa612fbcd2b76c86e01a65efc5156e +size 2716069184 diff --git a/Qwen3-4B-Thinking-2507-Genius-Buddy.Q4_K_S.gguf b/Qwen3-4B-Thinking-2507-Genius-Buddy.Q4_K_S.gguf new file mode 100644 index 0000000..fa0a004 --- /dev/null +++ b/Qwen3-4B-Thinking-2507-Genius-Buddy.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0887d2768e013b4db17bba84f889e35f60908a1bb57b5a9cb53ec7b8f78bed98 +size 2602097984 diff --git a/Qwen3-4B-Thinking-2507-Genius-Buddy.Q5_K_M.gguf b/Qwen3-4B-Thinking-2507-Genius-Buddy.Q5_K_M.gguf new file mode 100644 index 0000000..daba820 --- /dev/null +++ b/Qwen3-4B-Thinking-2507-Genius-Buddy.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4900a4d2d270d4b27b4a25f280c1b37e3f654972fe10d68667a0f9da313c2dee +size 3156921664 diff --git a/Qwen3-4B-Thinking-2507-Genius-Buddy.Q5_K_S.gguf b/Qwen3-4B-Thinking-2507-Genius-Buddy.Q5_K_S.gguf new file mode 100644 index 0000000..683d770 --- /dev/null +++ b/Qwen3-4B-Thinking-2507-Genius-Buddy.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e052ab07c3931c969b40af1e51e84edc9ce73d49a4864ef1bc8d93c6d45ca0af +size 3091119424 diff --git a/Qwen3-4B-Thinking-2507-Genius-Buddy.Q6_K.gguf b/Qwen3-4B-Thinking-2507-Genius-Buddy.Q6_K.gguf new file mode 100644 index 0000000..0ca466f --- /dev/null +++ b/Qwen3-4B-Thinking-2507-Genius-Buddy.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e282d7967a9eb007f18883a9635fc0621e967b4b3bd995f7c9e3227b7dfc4f11 +size 3625327424 diff --git a/Qwen3-4B-Thinking-2507-Genius-Buddy.Q8_0.gguf b/Qwen3-4B-Thinking-2507-Genius-Buddy.Q8_0.gguf new file mode 100644 index 0000000..14fdf27 --- /dev/null +++ b/Qwen3-4B-Thinking-2507-Genius-Buddy.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e362808cbaedbfc541da44b6ebdf469afaae2dcdaeedd3b17743902a7a05cdd +size 4693671744 diff --git a/Qwen3-4B-Thinking-2507-Genius-Buddy.f16.gguf b/Qwen3-4B-Thinking-2507-Genius-Buddy.f16.gguf new file mode 100644 index 0000000..66bf6fe --- /dev/null +++ b/Qwen3-4B-Thinking-2507-Genius-Buddy.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9595ffd987b43c98fe8f57fa67b725e53e1f29c650d1c5e65391c36f23e792f2 +size 8829198144 diff --git a/README.md b/README.md new file mode 100644 index 0000000..8e8c940 --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: rikunarita/Qwen3-4B-Thinking-2507-Genius-Buddy +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- qwen3 +--- +## About + + + + + + + + + +static quants of https://huggingface.co/rikunarita/Qwen3-4B-Thinking-2507-Genius-Buddy + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-4B-Thinking-2507-Genius-Buddy-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-Genius-Buddy-GGUF/resolve/main/Qwen3-4B-Thinking-2507-Genius-Buddy.Q2_K.gguf) | Q2_K | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-Genius-Buddy-GGUF/resolve/main/Qwen3-4B-Thinking-2507-Genius-Buddy.Q3_K_S.gguf) | Q3_K_S | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-Genius-Buddy-GGUF/resolve/main/Qwen3-4B-Thinking-2507-Genius-Buddy.Q3_K_M.gguf) | Q3_K_M | 2.3 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-Genius-Buddy-GGUF/resolve/main/Qwen3-4B-Thinking-2507-Genius-Buddy.Q3_K_L.gguf) | Q3_K_L | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-Genius-Buddy-GGUF/resolve/main/Qwen3-4B-Thinking-2507-Genius-Buddy.IQ4_XS.gguf) | IQ4_XS | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-Genius-Buddy-GGUF/resolve/main/Qwen3-4B-Thinking-2507-Genius-Buddy.Q4_K_S.gguf) | Q4_K_S | 2.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-Genius-Buddy-GGUF/resolve/main/Qwen3-4B-Thinking-2507-Genius-Buddy.Q4_K_M.gguf) | Q4_K_M | 2.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-Genius-Buddy-GGUF/resolve/main/Qwen3-4B-Thinking-2507-Genius-Buddy.Q5_K_S.gguf) | Q5_K_S | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-Genius-Buddy-GGUF/resolve/main/Qwen3-4B-Thinking-2507-Genius-Buddy.Q5_K_M.gguf) | Q5_K_M | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-Genius-Buddy-GGUF/resolve/main/Qwen3-4B-Thinking-2507-Genius-Buddy.Q6_K.gguf) | Q6_K | 3.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-Genius-Buddy-GGUF/resolve/main/Qwen3-4B-Thinking-2507-Genius-Buddy.Q8_0.gguf) | Q8_0 | 4.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-Genius-Buddy-GGUF/resolve/main/Qwen3-4B-Thinking-2507-Genius-Buddy.f16.gguf) | f16 | 8.9 | 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. + +