commit 5823b571f12435c4cce58dcf5ef0c73c2a6cd01f Author: ModelHub XC Date: Sun May 31 10:45:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/FluentlyQwen3-Coder-4B-0909-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..6cce7c3 --- /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 +FluentlyQwen3-Coder-4B-0909.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +FluentlyQwen3-Coder-4B-0909.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +FluentlyQwen3-Coder-4B-0909.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +FluentlyQwen3-Coder-4B-0909.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +FluentlyQwen3-Coder-4B-0909.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +FluentlyQwen3-Coder-4B-0909.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +FluentlyQwen3-Coder-4B-0909.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +FluentlyQwen3-Coder-4B-0909.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +FluentlyQwen3-Coder-4B-0909.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +FluentlyQwen3-Coder-4B-0909.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +FluentlyQwen3-Coder-4B-0909.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +FluentlyQwen3-Coder-4B-0909.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/FluentlyQwen3-Coder-4B-0909.IQ4_XS.gguf b/FluentlyQwen3-Coder-4B-0909.IQ4_XS.gguf new file mode 100644 index 0000000..50c5ca9 --- /dev/null +++ b/FluentlyQwen3-Coder-4B-0909.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77a5ce12619ade2960381c84efdd1effbcb51dcb1ad153668e35b9d12f9d6b12 +size 2286317152 diff --git a/FluentlyQwen3-Coder-4B-0909.Q2_K.gguf b/FluentlyQwen3-Coder-4B-0909.Q2_K.gguf new file mode 100644 index 0000000..ac85315 --- /dev/null +++ b/FluentlyQwen3-Coder-4B-0909.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a0eb00d176b92b8eb555578825506a19d7312969fee0d153a57d7b1e8f96d50 +size 1669500512 diff --git a/FluentlyQwen3-Coder-4B-0909.Q3_K_L.gguf b/FluentlyQwen3-Coder-4B-0909.Q3_K_L.gguf new file mode 100644 index 0000000..90c0e01 --- /dev/null +++ b/FluentlyQwen3-Coder-4B-0909.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:321d2faf3d4c308140fe626bbb01f5b2621130d03bda6a8d64d18c5ae6fcb1dd +size 2239786592 diff --git a/FluentlyQwen3-Coder-4B-0909.Q3_K_M.gguf b/FluentlyQwen3-Coder-4B-0909.Q3_K_M.gguf new file mode 100644 index 0000000..d141421 --- /dev/null +++ b/FluentlyQwen3-Coder-4B-0909.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b20e9d84fa3e9fbdbdd59c40e7a52627d6e9ee477461371deffd43cf0be0caf +size 2075618912 diff --git a/FluentlyQwen3-Coder-4B-0909.Q3_K_S.gguf b/FluentlyQwen3-Coder-4B-0909.Q3_K_S.gguf new file mode 100644 index 0000000..95a76d0 --- /dev/null +++ b/FluentlyQwen3-Coder-4B-0909.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:481d4e425c6b160de9d5c276c64dd832ab279aca1f4a45bf2ebcb0706941aceb +size 1886998112 diff --git a/FluentlyQwen3-Coder-4B-0909.Q4_K_M.gguf b/FluentlyQwen3-Coder-4B-0909.Q4_K_M.gguf new file mode 100644 index 0000000..494a384 --- /dev/null +++ b/FluentlyQwen3-Coder-4B-0909.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ffe93dc9cc2257d2efbbd7225dc620d1be9427c758b762d09c13c9d2fe6bedc0 +size 2497281632 diff --git a/FluentlyQwen3-Coder-4B-0909.Q4_K_S.gguf b/FluentlyQwen3-Coder-4B-0909.Q4_K_S.gguf new file mode 100644 index 0000000..7054d6e --- /dev/null +++ b/FluentlyQwen3-Coder-4B-0909.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4808e4b2d41796aec0a706e50228be10b9976968b5b4626a6931e5dab063fd5d +size 2383310432 diff --git a/FluentlyQwen3-Coder-4B-0909.Q5_K_M.gguf b/FluentlyQwen3-Coder-4B-0909.Q5_K_M.gguf new file mode 100644 index 0000000..73dd6e4 --- /dev/null +++ b/FluentlyQwen3-Coder-4B-0909.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3989e84bc657b54271fffa8b0f8f7055337ded29baa1bd01f659b346a1663a1f +size 2889514592 diff --git a/FluentlyQwen3-Coder-4B-0909.Q5_K_S.gguf b/FluentlyQwen3-Coder-4B-0909.Q5_K_S.gguf new file mode 100644 index 0000000..2dd0058 --- /dev/null +++ b/FluentlyQwen3-Coder-4B-0909.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:007378d72a6a28b5e2b97e755373c657d3e16389f3cc8e09589a96ead6c63a10 +size 2823712352 diff --git a/FluentlyQwen3-Coder-4B-0909.Q6_K.gguf b/FluentlyQwen3-Coder-4B-0909.Q6_K.gguf new file mode 100644 index 0000000..8e282b6 --- /dev/null +++ b/FluentlyQwen3-Coder-4B-0909.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:617d8f3987a980bedce5da403a0dd6442e2d69aa8063a7a1c56d376e293490b2 +size 3306262112 diff --git a/FluentlyQwen3-Coder-4B-0909.Q8_0.gguf b/FluentlyQwen3-Coder-4B-0909.Q8_0.gguf new file mode 100644 index 0000000..8c2caed --- /dev/null +++ b/FluentlyQwen3-Coder-4B-0909.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c69bba8b3e9b4bef1ba8db79604f880fdac2002441c60751485bf15c244d24eb +size 4280406112 diff --git a/FluentlyQwen3-Coder-4B-0909.f16.gguf b/FluentlyQwen3-Coder-4B-0909.f16.gguf new file mode 100644 index 0000000..21cd404 --- /dev/null +++ b/FluentlyQwen3-Coder-4B-0909.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abe1d8ecf5a2905a84e7b8ac44f298ecf8ad2a612057d055f38bc3a520471e5f +size 8051286112 diff --git a/README.md b/README.md new file mode 100644 index 0000000..6af423e --- /dev/null +++ b/README.md @@ -0,0 +1,88 @@ +--- +base_model: fluently/FluentlyQwen3-Coder-4B-0909 +datasets: +- nvidia/OpenCodeReasoning +language: +- en +- ru +- code +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- fluently +- fluently-lm +- qwen3 +- coder +- coding +- trained +- merged +- sft +- trl +- unsloth +- axolotl +--- +## About + + + + + + + + + +static quants of https://huggingface.co/fluently/FluentlyQwen3-Coder-4B-0909 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#FluentlyQwen3-Coder-4B-0909-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/FluentlyQwen3-Coder-4B-0909-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/FluentlyQwen3-Coder-4B-0909-GGUF/resolve/main/FluentlyQwen3-Coder-4B-0909.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/FluentlyQwen3-Coder-4B-0909-GGUF/resolve/main/FluentlyQwen3-Coder-4B-0909.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/FluentlyQwen3-Coder-4B-0909-GGUF/resolve/main/FluentlyQwen3-Coder-4B-0909.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/FluentlyQwen3-Coder-4B-0909-GGUF/resolve/main/FluentlyQwen3-Coder-4B-0909.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/FluentlyQwen3-Coder-4B-0909-GGUF/resolve/main/FluentlyQwen3-Coder-4B-0909.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/FluentlyQwen3-Coder-4B-0909-GGUF/resolve/main/FluentlyQwen3-Coder-4B-0909.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/FluentlyQwen3-Coder-4B-0909-GGUF/resolve/main/FluentlyQwen3-Coder-4B-0909.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/FluentlyQwen3-Coder-4B-0909-GGUF/resolve/main/FluentlyQwen3-Coder-4B-0909.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/FluentlyQwen3-Coder-4B-0909-GGUF/resolve/main/FluentlyQwen3-Coder-4B-0909.Q5_K_M.gguf) | Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/FluentlyQwen3-Coder-4B-0909-GGUF/resolve/main/FluentlyQwen3-Coder-4B-0909.Q6_K.gguf) | Q6_K | 3.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/FluentlyQwen3-Coder-4B-0909-GGUF/resolve/main/FluentlyQwen3-Coder-4B-0909.Q8_0.gguf) | Q8_0 | 4.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/FluentlyQwen3-Coder-4B-0909-GGUF/resolve/main/FluentlyQwen3-Coder-4B-0909.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. + +