commit e04bae63945708bde37d78993bd8d5543f052fe3 Author: ModelHub XC Date: Tue Jun 2 10:46:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Bootes-Qwen3_Coder-Reasoning-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..83bef12 --- /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 +Bootes-Qwen3_Coder-Reasoning.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Bootes-Qwen3_Coder-Reasoning.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Bootes-Qwen3_Coder-Reasoning.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Bootes-Qwen3_Coder-Reasoning.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Bootes-Qwen3_Coder-Reasoning.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Bootes-Qwen3_Coder-Reasoning.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Bootes-Qwen3_Coder-Reasoning.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Bootes-Qwen3_Coder-Reasoning.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Bootes-Qwen3_Coder-Reasoning.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Bootes-Qwen3_Coder-Reasoning.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Bootes-Qwen3_Coder-Reasoning.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Bootes-Qwen3_Coder-Reasoning.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Bootes-Qwen3_Coder-Reasoning.IQ4_XS.gguf b/Bootes-Qwen3_Coder-Reasoning.IQ4_XS.gguf new file mode 100644 index 0000000..9bc88df --- /dev/null +++ b/Bootes-Qwen3_Coder-Reasoning.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d7ed886a42e0c3cde1c686e49bdfe7fefa120922cf06664137717339234d71c +size 2286318112 diff --git a/Bootes-Qwen3_Coder-Reasoning.Q2_K.gguf b/Bootes-Qwen3_Coder-Reasoning.Q2_K.gguf new file mode 100644 index 0000000..b35b79d --- /dev/null +++ b/Bootes-Qwen3_Coder-Reasoning.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42457f2b1fcbcc238b324e7865358c126e5a122c74b19380f4a1522c07565008 +size 1669501472 diff --git a/Bootes-Qwen3_Coder-Reasoning.Q3_K_L.gguf b/Bootes-Qwen3_Coder-Reasoning.Q3_K_L.gguf new file mode 100644 index 0000000..cc6c44d --- /dev/null +++ b/Bootes-Qwen3_Coder-Reasoning.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2251aecc5b413622d2bf2b94fa093fa17ec6b175e6bf1bfc0b154c7a3f69515f +size 2239787552 diff --git a/Bootes-Qwen3_Coder-Reasoning.Q3_K_M.gguf b/Bootes-Qwen3_Coder-Reasoning.Q3_K_M.gguf new file mode 100644 index 0000000..b7d661c --- /dev/null +++ b/Bootes-Qwen3_Coder-Reasoning.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4cc2995247b3cca43255f0eb155b974398d7d68241f227b6b1543fc964893279 +size 2075619872 diff --git a/Bootes-Qwen3_Coder-Reasoning.Q3_K_S.gguf b/Bootes-Qwen3_Coder-Reasoning.Q3_K_S.gguf new file mode 100644 index 0000000..6e42614 --- /dev/null +++ b/Bootes-Qwen3_Coder-Reasoning.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ee9462b0b12aa119883e7915989d2ad226197cfb1e08fc0cbfd279e57de1858 +size 1886999072 diff --git a/Bootes-Qwen3_Coder-Reasoning.Q4_K_M.gguf b/Bootes-Qwen3_Coder-Reasoning.Q4_K_M.gguf new file mode 100644 index 0000000..fb9be0f --- /dev/null +++ b/Bootes-Qwen3_Coder-Reasoning.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c4c846af43cd9b00bc9fafa7ddedc7f313744b829c22d26045b41da02d9a38a +size 2497282592 diff --git a/Bootes-Qwen3_Coder-Reasoning.Q4_K_S.gguf b/Bootes-Qwen3_Coder-Reasoning.Q4_K_S.gguf new file mode 100644 index 0000000..b44ced8 --- /dev/null +++ b/Bootes-Qwen3_Coder-Reasoning.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a0c5f328b13a1e43678a5df02b0015b0cfe8aa7e9443015e3e3518eed41e0d6 +size 2383311392 diff --git a/Bootes-Qwen3_Coder-Reasoning.Q5_K_M.gguf b/Bootes-Qwen3_Coder-Reasoning.Q5_K_M.gguf new file mode 100644 index 0000000..dff900f --- /dev/null +++ b/Bootes-Qwen3_Coder-Reasoning.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:daceffc14bbac0b7b80770da156302da1b1d3699602574c2526f16299cf00a0a +size 2889515552 diff --git a/Bootes-Qwen3_Coder-Reasoning.Q5_K_S.gguf b/Bootes-Qwen3_Coder-Reasoning.Q5_K_S.gguf new file mode 100644 index 0000000..115a375 --- /dev/null +++ b/Bootes-Qwen3_Coder-Reasoning.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb761558ba327767637c5f35d47379b0bd82ccfc2a1c2f3dce7617000071fa4c +size 2823713312 diff --git a/Bootes-Qwen3_Coder-Reasoning.Q6_K.gguf b/Bootes-Qwen3_Coder-Reasoning.Q6_K.gguf new file mode 100644 index 0000000..90ba2d2 --- /dev/null +++ b/Bootes-Qwen3_Coder-Reasoning.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:343a700f8dd64ae648dc894e1e73d35caa87096b77237284c204a523b1317d52 +size 3306263072 diff --git a/Bootes-Qwen3_Coder-Reasoning.Q8_0.gguf b/Bootes-Qwen3_Coder-Reasoning.Q8_0.gguf new file mode 100644 index 0000000..0ee1b22 --- /dev/null +++ b/Bootes-Qwen3_Coder-Reasoning.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12f4f538178867803327b9dfaa8e99ae35caa1204aba53c938ad2e0616836243 +size 4280407072 diff --git a/Bootes-Qwen3_Coder-Reasoning.f16.gguf b/Bootes-Qwen3_Coder-Reasoning.f16.gguf new file mode 100644 index 0000000..c458ac0 --- /dev/null +++ b/Bootes-Qwen3_Coder-Reasoning.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e36287a953f96733c8f312015e75d95578571d5ca4c1d3aa8fbdc482c6fc3ddc +size 8051287072 diff --git a/README.md b/README.md new file mode 100644 index 0000000..b942b61 --- /dev/null +++ b/README.md @@ -0,0 +1,83 @@ +--- +base_model: prithivMLmods/Bootes-Qwen3_Coder-Reasoning +datasets: +- nvidia/OpenCodeReasoning +- efficientscaling/Z1-Code-Reasoning-107K +- HuggingFaceH4/CodeAlpaca_20K +- mlabonne/FineTome-100k +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- moe +- text-generation-inference +- code +- math +- mot +- coder +- stem +- trl +--- +## About + + + + + + +static quants of https://huggingface.co/prithivMLmods/Bootes-Qwen3_Coder-Reasoning + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Bootes-Qwen3_Coder-Reasoning-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Bootes-Qwen3_Coder-Reasoning-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/Bootes-Qwen3_Coder-Reasoning-GGUF/resolve/main/Bootes-Qwen3_Coder-Reasoning.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Bootes-Qwen3_Coder-Reasoning-GGUF/resolve/main/Bootes-Qwen3_Coder-Reasoning.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Bootes-Qwen3_Coder-Reasoning-GGUF/resolve/main/Bootes-Qwen3_Coder-Reasoning.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Bootes-Qwen3_Coder-Reasoning-GGUF/resolve/main/Bootes-Qwen3_Coder-Reasoning.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Bootes-Qwen3_Coder-Reasoning-GGUF/resolve/main/Bootes-Qwen3_Coder-Reasoning.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Bootes-Qwen3_Coder-Reasoning-GGUF/resolve/main/Bootes-Qwen3_Coder-Reasoning.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Bootes-Qwen3_Coder-Reasoning-GGUF/resolve/main/Bootes-Qwen3_Coder-Reasoning.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Bootes-Qwen3_Coder-Reasoning-GGUF/resolve/main/Bootes-Qwen3_Coder-Reasoning.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Bootes-Qwen3_Coder-Reasoning-GGUF/resolve/main/Bootes-Qwen3_Coder-Reasoning.Q5_K_M.gguf) | Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Bootes-Qwen3_Coder-Reasoning-GGUF/resolve/main/Bootes-Qwen3_Coder-Reasoning.Q6_K.gguf) | Q6_K | 3.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Bootes-Qwen3_Coder-Reasoning-GGUF/resolve/main/Bootes-Qwen3_Coder-Reasoning.Q8_0.gguf) | Q8_0 | 4.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Bootes-Qwen3_Coder-Reasoning-GGUF/resolve/main/Bootes-Qwen3_Coder-Reasoning.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. + +