commit f5424a4cfbe9e4b59ce61109af7333a2f26727f3 Author: ModelHub XC Date: Sat Apr 11 17:07:01 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-0.6B-Code-Expert-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d1d515b --- /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 +Qwen3-0.6B-Code-Expert.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Code-Expert.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Code-Expert.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Code-Expert.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Code-Expert.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Code-Expert.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Code-Expert.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Code-Expert.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Code-Expert.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Code-Expert.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Code-Expert.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Code-Expert.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-0.6B-Code-Expert.IQ4_XS.gguf b/Qwen3-0.6B-Code-Expert.IQ4_XS.gguf new file mode 100644 index 0000000..e05de17 --- /dev/null +++ b/Qwen3-0.6B-Code-Expert.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1700f70df2edf86291dfd77ef5b28035cb6cd7d39708359f0ee64a3a7255fdce +size 369279360 diff --git a/Qwen3-0.6B-Code-Expert.Q2_K.gguf b/Qwen3-0.6B-Code-Expert.Q2_K.gguf new file mode 100644 index 0000000..26cb913 --- /dev/null +++ b/Qwen3-0.6B-Code-Expert.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c563cb2b3eaac1018bd960a5279abb0bd5013a12aea7073ff1561002b3f40d2 +size 296239488 diff --git a/Qwen3-0.6B-Code-Expert.Q3_K_L.gguf b/Qwen3-0.6B-Code-Expert.Q3_K_L.gguf new file mode 100644 index 0000000..0d95f8f --- /dev/null +++ b/Qwen3-0.6B-Code-Expert.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78d540bb90c289b9035ec7a8fccdb126fed3e2cd64fce5c79184ea970d18f8c3 +size 368492928 diff --git a/Qwen3-0.6B-Code-Expert.Q3_K_M.gguf b/Qwen3-0.6B-Code-Expert.Q3_K_M.gguf new file mode 100644 index 0000000..a17e997 --- /dev/null +++ b/Qwen3-0.6B-Code-Expert.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be652f680d13ded8ac6fc2f97d9d90059e758562a08c3e0f59b7b5518748664b +size 347128192 diff --git a/Qwen3-0.6B-Code-Expert.Q3_K_S.gguf b/Qwen3-0.6B-Code-Expert.Q3_K_S.gguf new file mode 100644 index 0000000..156df08 --- /dev/null +++ b/Qwen3-0.6B-Code-Expert.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3fd8aa45e1620c9db7f532023d554a0f47a619145120a960b617ac7fef0100c6 +size 323076480 diff --git a/Qwen3-0.6B-Code-Expert.Q4_K_M.gguf b/Qwen3-0.6B-Code-Expert.Q4_K_M.gguf new file mode 100644 index 0000000..8f6778c --- /dev/null +++ b/Qwen3-0.6B-Code-Expert.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69d94acbabd7ae103b6dd6145db9c75230c561de06567b61ab39b925a5c56b97 +size 396706176 diff --git a/Qwen3-0.6B-Code-Expert.Q4_K_S.gguf b/Qwen3-0.6B-Code-Expert.Q4_K_S.gguf new file mode 100644 index 0000000..1d0374d --- /dev/null +++ b/Qwen3-0.6B-Code-Expert.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07362412f6fd4d68c3558a32f5ea075c8d139932b799cb7e118413550394faee +size 383271296 diff --git a/Qwen3-0.6B-Code-Expert.Q5_K_M.gguf b/Qwen3-0.6B-Code-Expert.Q5_K_M.gguf new file mode 100644 index 0000000..3fe5290 --- /dev/null +++ b/Qwen3-0.6B-Code-Expert.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:860b2538085d868aacbcb4fe67992803fd5aefc234b6f372d6221b8ba3d5f2e7 +size 444416384 diff --git a/Qwen3-0.6B-Code-Expert.Q5_K_S.gguf b/Qwen3-0.6B-Code-Expert.Q5_K_S.gguf new file mode 100644 index 0000000..7a0fc09 --- /dev/null +++ b/Qwen3-0.6B-Code-Expert.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74ea2cc1a2c244ba031f11fcb3987cfbe6ffaf799166568a731ef43dfd72c3d9 +size 436617600 diff --git a/Qwen3-0.6B-Code-Expert.Q6_K.gguf b/Qwen3-0.6B-Code-Expert.Q6_K.gguf new file mode 100644 index 0000000..a9d6c93 --- /dev/null +++ b/Qwen3-0.6B-Code-Expert.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b3244d61aeee92dc2a08580b7da0969e80dced348d9300806d803cd9ea6e93f +size 495108480 diff --git a/Qwen3-0.6B-Code-Expert.Q8_0.gguf b/Qwen3-0.6B-Code-Expert.Q8_0.gguf new file mode 100644 index 0000000..64d6200 --- /dev/null +++ b/Qwen3-0.6B-Code-Expert.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e026c41f356275576b312ec7f8d80efa4e1931b3d39d1c89a9798339ef61405 +size 639448448 diff --git a/Qwen3-0.6B-Code-Expert.f16.gguf b/Qwen3-0.6B-Code-Expert.f16.gguf new file mode 100644 index 0000000..269c022 --- /dev/null +++ b/Qwen3-0.6B-Code-Expert.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d329b65308b1fc13f1aacb87395aff61e24e7baf18b95da4a9a86b9393f8f604 +size 1198183808 diff --git a/README.md b/README.md new file mode 100644 index 0000000..32e2a07 --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: suayptalha/Qwen3-0.6B-Code-Expert +datasets: +- nvidia/OpenCodeReasoning +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- unsloth +- trl +- sft +- code +- reasoning +--- +## About + + + + + + +static quants of https://huggingface.co/suayptalha/Qwen3-0.6B-Code-Expert + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-0.6B-Code-Expert-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/Qwen3-0.6B-Code-Expert-GGUF/resolve/main/Qwen3-0.6B-Code-Expert.Q2_K.gguf) | Q2_K | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Code-Expert-GGUF/resolve/main/Qwen3-0.6B-Code-Expert.Q3_K_S.gguf) | Q3_K_S | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Code-Expert-GGUF/resolve/main/Qwen3-0.6B-Code-Expert.Q3_K_M.gguf) | Q3_K_M | 0.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Code-Expert-GGUF/resolve/main/Qwen3-0.6B-Code-Expert.Q3_K_L.gguf) | Q3_K_L | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Code-Expert-GGUF/resolve/main/Qwen3-0.6B-Code-Expert.IQ4_XS.gguf) | IQ4_XS | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Code-Expert-GGUF/resolve/main/Qwen3-0.6B-Code-Expert.Q4_K_S.gguf) | Q4_K_S | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Code-Expert-GGUF/resolve/main/Qwen3-0.6B-Code-Expert.Q4_K_M.gguf) | Q4_K_M | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Code-Expert-GGUF/resolve/main/Qwen3-0.6B-Code-Expert.Q5_K_S.gguf) | Q5_K_S | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Code-Expert-GGUF/resolve/main/Qwen3-0.6B-Code-Expert.Q5_K_M.gguf) | Q5_K_M | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Code-Expert-GGUF/resolve/main/Qwen3-0.6B-Code-Expert.Q6_K.gguf) | Q6_K | 0.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Code-Expert-GGUF/resolve/main/Qwen3-0.6B-Code-Expert.Q8_0.gguf) | Q8_0 | 0.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Code-Expert-GGUF/resolve/main/Qwen3-0.6B-Code-Expert.f16.gguf) | f16 | 1.3 | 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. + +