commit 22e8ebe4edf3ef6a75170391b26ac34151a4b10d Author: ModelHub XC Date: Sun Jul 19 03:07:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2.5-Coder-3B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..137681a --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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 +Qwen2.5-Coder-3B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-3B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-3B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-3B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-3B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-3B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-3B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-3B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-3B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-3B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-3B.f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-3B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-3B.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-Coder-3B.IQ4_XS.gguf b/Qwen2.5-Coder-3B.IQ4_XS.gguf new file mode 100644 index 0000000..3df0440 --- /dev/null +++ b/Qwen2.5-Coder-3B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f32c2a8bfe03113b1f523236122597139899cfe56467ffddbbb015e2c3d2e4e6 +size 1753185536 diff --git a/Qwen2.5-Coder-3B.Q2_K.gguf b/Qwen2.5-Coder-3B.Q2_K.gguf new file mode 100644 index 0000000..081cf5c --- /dev/null +++ b/Qwen2.5-Coder-3B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b40d0bd86691385d7ac3e7fcdbd428b6d6044b291c94aec53f814bb03882860 +size 1274756352 diff --git a/Qwen2.5-Coder-3B.Q3_K_L.gguf b/Qwen2.5-Coder-3B.Q3_K_L.gguf new file mode 100644 index 0000000..f31fc81 --- /dev/null +++ b/Qwen2.5-Coder-3B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51faa8b09c2e1e4a518ae0b8cec2ab691e91b9a5f8cf5f7cc7e7eaf15e3e1656 +size 1707392256 diff --git a/Qwen2.5-Coder-3B.Q3_K_M.gguf b/Qwen2.5-Coder-3B.Q3_K_M.gguf new file mode 100644 index 0000000..8925af9 --- /dev/null +++ b/Qwen2.5-Coder-3B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc423e6996e31edcc2fd1b49b5a2cf8a09b4227736bf7a3cd2024e041233c122 +size 1590476032 diff --git a/Qwen2.5-Coder-3B.Q3_K_S.gguf b/Qwen2.5-Coder-3B.Q3_K_S.gguf new file mode 100644 index 0000000..9454666 --- /dev/null +++ b/Qwen2.5-Coder-3B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae17059e5ed6cbf9a7bf03aab7d84bb61eb94c48088f6d8a00d626f7b5cdcd11 +size 1454357760 diff --git a/Qwen2.5-Coder-3B.Q4_0_4_4.gguf b/Qwen2.5-Coder-3B.Q4_0_4_4.gguf new file mode 100644 index 0000000..7c5f0fc --- /dev/null +++ b/Qwen2.5-Coder-3B.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:315a750e453769506056963973c7a56e065b5c0fde07b0c5c10bdda2f0695b4e +size 1822850304 diff --git a/Qwen2.5-Coder-3B.Q4_K_M.gguf b/Qwen2.5-Coder-3B.Q4_K_M.gguf new file mode 100644 index 0000000..5e95739 --- /dev/null +++ b/Qwen2.5-Coder-3B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a92a7058b93554da9071cd36bbfe9ec9e2431c896ecfa7d629d4411404452ab7 +size 1929903360 diff --git a/Qwen2.5-Coder-3B.Q4_K_S.gguf b/Qwen2.5-Coder-3B.Q4_K_S.gguf new file mode 100644 index 0000000..1d1fe6c --- /dev/null +++ b/Qwen2.5-Coder-3B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8898098317020b993ed246a9021e8668ef9050c20a044d4561e976a6b85c4477 +size 1834384640 diff --git a/Qwen2.5-Coder-3B.Q5_K_M.gguf b/Qwen2.5-Coder-3B.Q5_K_M.gguf new file mode 100644 index 0000000..1d43266 --- /dev/null +++ b/Qwen2.5-Coder-3B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c6d63d3a9593e3c7c241e181939b9c847df489af619ba61c26d0e8777948bd8 +size 2224815360 diff --git a/Qwen2.5-Coder-3B.Q5_K_S.gguf b/Qwen2.5-Coder-3B.Q5_K_S.gguf new file mode 100644 index 0000000..d6591d3 --- /dev/null +++ b/Qwen2.5-Coder-3B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8db5c016f282967dd019c64129ae395457f0f76347fc04e3b1c7ae6513108e8f +size 2169666816 diff --git a/Qwen2.5-Coder-3B.Q6_K.gguf b/Qwen2.5-Coder-3B.Q6_K.gguf new file mode 100644 index 0000000..77d5c98 --- /dev/null +++ b/Qwen2.5-Coder-3B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c1ee0e2554a2c01ddc920e9df4f14ca28088c8d9ab385f403850b8ac4ab9c5e +size 2538159360 diff --git a/Qwen2.5-Coder-3B.Q8_0.gguf b/Qwen2.5-Coder-3B.Q8_0.gguf new file mode 100644 index 0000000..4e43e8c --- /dev/null +++ b/Qwen2.5-Coder-3B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3427f9c9511285b0c1898efd3e68b6e368f27b53456303f27294385e9b3fa87b +size 3285476608 diff --git a/Qwen2.5-Coder-3B.f16.gguf b/Qwen2.5-Coder-3B.f16.gguf new file mode 100644 index 0000000..151c0dd --- /dev/null +++ b/Qwen2.5-Coder-3B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73b9018ba78cafdd396dde69b63e8058bb8400d0c3753ebf311b0a0f21736418 +size 6178317568 diff --git a/README.md b/README.md new file mode 100644 index 0000000..10c2e45 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: Qwen/Qwen2.5-Coder-3B +language: +- en +library_name: transformers +license: other +license_link: https://huggingface.co/Qwen/Qwen2.5-Coder-3B/blob/main/LICENSE +license_name: qwen-research +quantized_by: mradermacher +tags: +- code +- qwen +- qwen-coder +- codeqwen +--- +## About + + + + + + +static quants of https://huggingface.co/Qwen/Qwen2.5-Coder-3B + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen2.5-Coder-3B-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/Qwen2.5-Coder-3B-GGUF/resolve/main/Qwen2.5-Coder-3B.Q2_K.gguf) | Q2_K | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-3B-GGUF/resolve/main/Qwen2.5-Coder-3B.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-3B-GGUF/resolve/main/Qwen2.5-Coder-3B.Q3_K_M.gguf) | Q3_K_M | 1.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-3B-GGUF/resolve/main/Qwen2.5-Coder-3B.Q3_K_L.gguf) | Q3_K_L | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-3B-GGUF/resolve/main/Qwen2.5-Coder-3B.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-3B-GGUF/resolve/main/Qwen2.5-Coder-3B.Q4_0_4_4.gguf) | Q4_0_4_4 | 1.9 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-3B-GGUF/resolve/main/Qwen2.5-Coder-3B.Q4_K_S.gguf) | Q4_K_S | 1.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-3B-GGUF/resolve/main/Qwen2.5-Coder-3B.Q4_K_M.gguf) | Q4_K_M | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-3B-GGUF/resolve/main/Qwen2.5-Coder-3B.Q5_K_S.gguf) | Q5_K_S | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-3B-GGUF/resolve/main/Qwen2.5-Coder-3B.Q5_K_M.gguf) | Q5_K_M | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-3B-GGUF/resolve/main/Qwen2.5-Coder-3B.Q6_K.gguf) | Q6_K | 2.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-3B-GGUF/resolve/main/Qwen2.5-Coder-3B.Q8_0.gguf) | Q8_0 | 3.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-3B-GGUF/resolve/main/Qwen2.5-Coder-3B.f16.gguf) | f16 | 6.3 | 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. + +