commit 91f5083afce18cead9be9654913a5cb0f65ed92c Author: ModelHub XC Date: Tue May 19 11:46:38 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-4B-Thinking-2507-Genius-Coder-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..63368fb --- /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-Coder.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Thinking-2507-Genius-Coder.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Thinking-2507-Genius-Coder.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Thinking-2507-Genius-Coder.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Thinking-2507-Genius-Coder.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Thinking-2507-Genius-Coder.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Thinking-2507-Genius-Coder.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Thinking-2507-Genius-Coder.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Thinking-2507-Genius-Coder.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Thinking-2507-Genius-Coder.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Thinking-2507-Genius-Coder.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Thinking-2507-Genius-Coder.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-4B-Thinking-2507-Genius-Coder.IQ4_XS.gguf b/Qwen3-4B-Thinking-2507-Genius-Coder.IQ4_XS.gguf new file mode 100644 index 0000000..f008c31 --- /dev/null +++ b/Qwen3-4B-Thinking-2507-Genius-Coder.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9583b912d336024da6bb7f6ec04f71ce8d5a3263725fea2c64fe37b3cc477196 +size 2492949856 diff --git a/Qwen3-4B-Thinking-2507-Genius-Coder.Q2_K.gguf b/Qwen3-4B-Thinking-2507-Genius-Coder.Q2_K.gguf new file mode 100644 index 0000000..6c71035 --- /dev/null +++ b/Qwen3-4B-Thinking-2507-Genius-Coder.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:937e27b92114e0b74e5ee2f272156e034516ab1bb5c877dae4d899541ab4d247 +size 1797126496 diff --git a/Qwen3-4B-Thinking-2507-Genius-Coder.Q3_K_L.gguf b/Qwen3-4B-Thinking-2507-Genius-Coder.Q3_K_L.gguf new file mode 100644 index 0000000..bedffcf --- /dev/null +++ b/Qwen3-4B-Thinking-2507-Genius-Coder.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:538157c1b9971af9b8699988852ca121a856727babf0d5c20e47e010d6280f99 +size 2406915936 diff --git a/Qwen3-4B-Thinking-2507-Genius-Coder.Q3_K_M.gguf b/Qwen3-4B-Thinking-2507-Genius-Coder.Q3_K_M.gguf new file mode 100644 index 0000000..46fe3b2 --- /dev/null +++ b/Qwen3-4B-Thinking-2507-Genius-Coder.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:818fdd00ffab5dd5258668f70aa7f24a1042fecb49e27916bfded060c2477e3b +size 2242748256 diff --git a/Qwen3-4B-Thinking-2507-Genius-Coder.Q3_K_S.gguf b/Qwen3-4B-Thinking-2507-Genius-Coder.Q3_K_S.gguf new file mode 100644 index 0000000..46301f9 --- /dev/null +++ b/Qwen3-4B-Thinking-2507-Genius-Coder.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9ce5cc73a8145a04c0b7a7e5671c13c584002d1475031d4578fffa8123c4098 +size 2054127456 diff --git a/Qwen3-4B-Thinking-2507-Genius-Coder.Q4_K_M.gguf b/Qwen3-4B-Thinking-2507-Genius-Coder.Q4_K_M.gguf new file mode 100644 index 0000000..29ea4f6 --- /dev/null +++ b/Qwen3-4B-Thinking-2507-Genius-Coder.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2868d27564887ab26b01b96354222d3c021f7461ffb2c3ebba436daa68022d4 +size 2716069216 diff --git a/Qwen3-4B-Thinking-2507-Genius-Coder.Q4_K_S.gguf b/Qwen3-4B-Thinking-2507-Genius-Coder.Q4_K_S.gguf new file mode 100644 index 0000000..8fc12b6 --- /dev/null +++ b/Qwen3-4B-Thinking-2507-Genius-Coder.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:716f4a58359d86a83281e5a41d2223a651f58b737d6c51afa99a5653987ec4f7 +size 2602098016 diff --git a/Qwen3-4B-Thinking-2507-Genius-Coder.Q5_K_M.gguf b/Qwen3-4B-Thinking-2507-Genius-Coder.Q5_K_M.gguf new file mode 100644 index 0000000..5ed6fc4 --- /dev/null +++ b/Qwen3-4B-Thinking-2507-Genius-Coder.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af86cc1124740ff06abca47d4281b9f6de0963758b37e97097a1a5f227415c6e +size 3156921696 diff --git a/Qwen3-4B-Thinking-2507-Genius-Coder.Q5_K_S.gguf b/Qwen3-4B-Thinking-2507-Genius-Coder.Q5_K_S.gguf new file mode 100644 index 0000000..49a72c5 --- /dev/null +++ b/Qwen3-4B-Thinking-2507-Genius-Coder.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdd992d0ccb772131f1a5dd6f0ad2680a6742a275f3b88ad5713ee2bc452e7fb +size 3091119456 diff --git a/Qwen3-4B-Thinking-2507-Genius-Coder.Q6_K.gguf b/Qwen3-4B-Thinking-2507-Genius-Coder.Q6_K.gguf new file mode 100644 index 0000000..7ec929b --- /dev/null +++ b/Qwen3-4B-Thinking-2507-Genius-Coder.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:789b5edbc2c2244b50edeeec9fbf9208f9caef4035429c1c70db6b1c65652744 +size 3625327456 diff --git a/Qwen3-4B-Thinking-2507-Genius-Coder.Q8_0.gguf b/Qwen3-4B-Thinking-2507-Genius-Coder.Q8_0.gguf new file mode 100644 index 0000000..19c4c6d --- /dev/null +++ b/Qwen3-4B-Thinking-2507-Genius-Coder.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1cd91aab98c7e8f81f3365c72211ae687c225d24330d760f5d15eb06b828b3b6 +size 4693671776 diff --git a/Qwen3-4B-Thinking-2507-Genius-Coder.f16.gguf b/Qwen3-4B-Thinking-2507-Genius-Coder.f16.gguf new file mode 100644 index 0000000..d0a048f --- /dev/null +++ b/Qwen3-4B-Thinking-2507-Genius-Coder.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c29180d1dcbfe4be44bc63ac5235e6fc8c7c85ad8a768629b87423ce028eff4 +size 8829198176 diff --git a/README.md b/README.md new file mode 100644 index 0000000..c6d2bf1 --- /dev/null +++ b/README.md @@ -0,0 +1,79 @@ +--- +base_model: rikunarita/Qwen3-4B-Thinking-2507-Genius-Coder +language: +- en +- zh +- ja +library_name: transformers +license: mit +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-Coder + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-4B-Thinking-2507-Genius-Coder-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-Coder-GGUF/resolve/main/Qwen3-4B-Thinking-2507-Genius-Coder.Q2_K.gguf) | Q2_K | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-Genius-Coder-GGUF/resolve/main/Qwen3-4B-Thinking-2507-Genius-Coder.Q3_K_S.gguf) | Q3_K_S | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-Genius-Coder-GGUF/resolve/main/Qwen3-4B-Thinking-2507-Genius-Coder.Q3_K_M.gguf) | Q3_K_M | 2.3 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-Genius-Coder-GGUF/resolve/main/Qwen3-4B-Thinking-2507-Genius-Coder.Q3_K_L.gguf) | Q3_K_L | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-Genius-Coder-GGUF/resolve/main/Qwen3-4B-Thinking-2507-Genius-Coder.IQ4_XS.gguf) | IQ4_XS | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-Genius-Coder-GGUF/resolve/main/Qwen3-4B-Thinking-2507-Genius-Coder.Q4_K_S.gguf) | Q4_K_S | 2.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-Genius-Coder-GGUF/resolve/main/Qwen3-4B-Thinking-2507-Genius-Coder.Q4_K_M.gguf) | Q4_K_M | 2.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-Genius-Coder-GGUF/resolve/main/Qwen3-4B-Thinking-2507-Genius-Coder.Q5_K_S.gguf) | Q5_K_S | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-Genius-Coder-GGUF/resolve/main/Qwen3-4B-Thinking-2507-Genius-Coder.Q5_K_M.gguf) | Q5_K_M | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-Genius-Coder-GGUF/resolve/main/Qwen3-4B-Thinking-2507-Genius-Coder.Q6_K.gguf) | Q6_K | 3.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-Genius-Coder-GGUF/resolve/main/Qwen3-4B-Thinking-2507-Genius-Coder.Q8_0.gguf) | Q8_0 | 4.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-Genius-Coder-GGUF/resolve/main/Qwen3-4B-Thinking-2507-Genius-Coder.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. + +