commit fde082d2d29bf7b487fd8e8be2251b6dd8a20151 Author: ModelHub XC Date: Sun Jul 19 03:25:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2.5-Coder-3B-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d5f8701 --- /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-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-3B-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-3B-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-3B-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-3B-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-3B-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-3B-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-3B-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-3B-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-3B-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-3B-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-3B-Instruct.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-3B-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-Coder-3B-Instruct.IQ4_XS.gguf b/Qwen2.5-Coder-3B-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..f61e895 --- /dev/null +++ b/Qwen2.5-Coder-3B-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:113f6d446027bc573b6c4e607a61d82ed70127dca1867c46b6e125eff2ba025d +size 1753185728 diff --git a/Qwen2.5-Coder-3B-Instruct.Q2_K.gguf b/Qwen2.5-Coder-3B-Instruct.Q2_K.gguf new file mode 100644 index 0000000..9ca059d --- /dev/null +++ b/Qwen2.5-Coder-3B-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7948193fba5c8b7ec708899eb7c766573bdd52b64a56ad4e1ad6cf5feb47f58 +size 1274756544 diff --git a/Qwen2.5-Coder-3B-Instruct.Q3_K_L.gguf b/Qwen2.5-Coder-3B-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..810f039 --- /dev/null +++ b/Qwen2.5-Coder-3B-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03d6aa8a9e4975e58c6fb42c2b7882863dfd15189fdc86b26c1ddb96c827d36a +size 1707392448 diff --git a/Qwen2.5-Coder-3B-Instruct.Q3_K_M.gguf b/Qwen2.5-Coder-3B-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..6e3d9d5 --- /dev/null +++ b/Qwen2.5-Coder-3B-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d8874d0ad918cc45a2d1b0ad514b7d718958751accd4e73107ba3edbf3e8ff1 +size 1590476224 diff --git a/Qwen2.5-Coder-3B-Instruct.Q3_K_S.gguf b/Qwen2.5-Coder-3B-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..b576f80 --- /dev/null +++ b/Qwen2.5-Coder-3B-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2cd7b21db7f1685475c60a7948d67257e4fce331dfdf1a796224848111792d7e +size 1454357952 diff --git a/Qwen2.5-Coder-3B-Instruct.Q4_0_4_4.gguf b/Qwen2.5-Coder-3B-Instruct.Q4_0_4_4.gguf new file mode 100644 index 0000000..d34df58 --- /dev/null +++ b/Qwen2.5-Coder-3B-Instruct.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3d348ddab97aa408608038cb025df8ca522fba2795da779f2d4b634a1b744f5 +size 1822850496 diff --git a/Qwen2.5-Coder-3B-Instruct.Q4_K_M.gguf b/Qwen2.5-Coder-3B-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..f1648b3 --- /dev/null +++ b/Qwen2.5-Coder-3B-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc595dffd29b12122343295348cee0524b53d2081c48fb4bd7b0002165b8f558 +size 1929903552 diff --git a/Qwen2.5-Coder-3B-Instruct.Q4_K_S.gguf b/Qwen2.5-Coder-3B-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..444272e --- /dev/null +++ b/Qwen2.5-Coder-3B-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77ae9237a3a8b1debe57a3bc208c59d129474aa81651f54addc250c95d4cbf5b +size 1834384832 diff --git a/Qwen2.5-Coder-3B-Instruct.Q5_K_M.gguf b/Qwen2.5-Coder-3B-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..b6e4319 --- /dev/null +++ b/Qwen2.5-Coder-3B-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9264e456f3508138e2eedfd9e4a9cf542e95709f9eb898f00158bd27eea7760 +size 2224815552 diff --git a/Qwen2.5-Coder-3B-Instruct.Q5_K_S.gguf b/Qwen2.5-Coder-3B-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..44640b7 --- /dev/null +++ b/Qwen2.5-Coder-3B-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:039ebb632a3bc4061f7c272f7c77ce6ab82892cfd876151b5b9ab035cacca78b +size 2169667008 diff --git a/Qwen2.5-Coder-3B-Instruct.Q6_K.gguf b/Qwen2.5-Coder-3B-Instruct.Q6_K.gguf new file mode 100644 index 0000000..38a1ba3 --- /dev/null +++ b/Qwen2.5-Coder-3B-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b2371f028475e43860ef88c0f02ab2db95e21c1792263186f808bee4f90faa8 +size 2538159552 diff --git a/Qwen2.5-Coder-3B-Instruct.Q8_0.gguf b/Qwen2.5-Coder-3B-Instruct.Q8_0.gguf new file mode 100644 index 0000000..295b153 --- /dev/null +++ b/Qwen2.5-Coder-3B-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b72c5235385b1a02a5473977b642080fc5860122809418f84899c822f1e81e4 +size 3285476800 diff --git a/Qwen2.5-Coder-3B-Instruct.f16.gguf b/Qwen2.5-Coder-3B-Instruct.f16.gguf new file mode 100644 index 0000000..da2065f --- /dev/null +++ b/Qwen2.5-Coder-3B-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e25d153e84e56d794d78072fb228ef1b6e587d6274914617c30c6837b65c46f +size 6178317760 diff --git a/README.md b/README.md new file mode 100644 index 0000000..75acf2f --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: Qwen/Qwen2.5-Coder-3B-Instruct +language: +- en +library_name: transformers +license: other +license_link: https://huggingface.co/Qwen/Qwen2.5-Coder-3B-Instruct/blob/main/LICENSE +license_name: qwen-research +quantized_by: mradermacher +tags: +- code +- codeqwen +- chat +- qwen +- qwen-coder +--- +## About + + + + + + +static quants of https://huggingface.co/Qwen/Qwen2.5-Coder-3B-Instruct + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen2.5-Coder-3B-Instruct-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-Instruct-GGUF/resolve/main/Qwen2.5-Coder-3B-Instruct.Q2_K.gguf) | Q2_K | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-3B-Instruct-GGUF/resolve/main/Qwen2.5-Coder-3B-Instruct.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-3B-Instruct-GGUF/resolve/main/Qwen2.5-Coder-3B-Instruct.Q3_K_M.gguf) | Q3_K_M | 1.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-3B-Instruct-GGUF/resolve/main/Qwen2.5-Coder-3B-Instruct.Q3_K_L.gguf) | Q3_K_L | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-3B-Instruct-GGUF/resolve/main/Qwen2.5-Coder-3B-Instruct.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-3B-Instruct-GGUF/resolve/main/Qwen2.5-Coder-3B-Instruct.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-Instruct-GGUF/resolve/main/Qwen2.5-Coder-3B-Instruct.Q4_K_S.gguf) | Q4_K_S | 1.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-3B-Instruct-GGUF/resolve/main/Qwen2.5-Coder-3B-Instruct.Q4_K_M.gguf) | Q4_K_M | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-3B-Instruct-GGUF/resolve/main/Qwen2.5-Coder-3B-Instruct.Q5_K_S.gguf) | Q5_K_S | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-3B-Instruct-GGUF/resolve/main/Qwen2.5-Coder-3B-Instruct.Q5_K_M.gguf) | Q5_K_M | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-3B-Instruct-GGUF/resolve/main/Qwen2.5-Coder-3B-Instruct.Q6_K.gguf) | Q6_K | 2.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-3B-Instruct-GGUF/resolve/main/Qwen2.5-Coder-3B-Instruct.Q8_0.gguf) | Q8_0 | 3.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-3B-Instruct-GGUF/resolve/main/Qwen2.5-Coder-3B-Instruct.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. + +