commit deb00439693ec77af51b4945380e8ae111ebba1f Author: ModelHub XC Date: Thu May 14 01:59:21 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/FluentlyQwen3-Coder-4B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e2be9e6 --- /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.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +FluentlyQwen3-Coder-4B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +FluentlyQwen3-Coder-4B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +FluentlyQwen3-Coder-4B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +FluentlyQwen3-Coder-4B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +FluentlyQwen3-Coder-4B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +FluentlyQwen3-Coder-4B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +FluentlyQwen3-Coder-4B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +FluentlyQwen3-Coder-4B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +FluentlyQwen3-Coder-4B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +FluentlyQwen3-Coder-4B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +FluentlyQwen3-Coder-4B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/FluentlyQwen3-Coder-4B.IQ4_XS.gguf b/FluentlyQwen3-Coder-4B.IQ4_XS.gguf new file mode 100644 index 0000000..25df10d --- /dev/null +++ b/FluentlyQwen3-Coder-4B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96be004d9634b4d2d9a29f6391d8fc27ab32bf3a14faeddf2d47992f094a319c +size 2286317088 diff --git a/FluentlyQwen3-Coder-4B.Q2_K.gguf b/FluentlyQwen3-Coder-4B.Q2_K.gguf new file mode 100644 index 0000000..f2e04bb --- /dev/null +++ b/FluentlyQwen3-Coder-4B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f7b7b8c61a688f875981ea9cb07e92dd7af019bc07dc0e5727aa8523bdc7af0 +size 1669500448 diff --git a/FluentlyQwen3-Coder-4B.Q3_K_L.gguf b/FluentlyQwen3-Coder-4B.Q3_K_L.gguf new file mode 100644 index 0000000..514c287 --- /dev/null +++ b/FluentlyQwen3-Coder-4B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e0b7c39825afa2892030e60c070afd5fc55d5f3bfd1d7f569856afbe0e4f62d +size 2239786528 diff --git a/FluentlyQwen3-Coder-4B.Q3_K_M.gguf b/FluentlyQwen3-Coder-4B.Q3_K_M.gguf new file mode 100644 index 0000000..ec1e77c --- /dev/null +++ b/FluentlyQwen3-Coder-4B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80363fff649977d8f8c2b2101ad97ab379c6afba9e3e14941a6cf0fe5c3ab42f +size 2075618848 diff --git a/FluentlyQwen3-Coder-4B.Q3_K_S.gguf b/FluentlyQwen3-Coder-4B.Q3_K_S.gguf new file mode 100644 index 0000000..7455968 --- /dev/null +++ b/FluentlyQwen3-Coder-4B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca40c59468c79df4bbfc6124a3b2573d80165dbac4f857868caa1ded8239e206 +size 1886998048 diff --git a/FluentlyQwen3-Coder-4B.Q4_K_M.gguf b/FluentlyQwen3-Coder-4B.Q4_K_M.gguf new file mode 100644 index 0000000..b5ea8b4 --- /dev/null +++ b/FluentlyQwen3-Coder-4B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef6abe62594cf94e5801f72de81fa62043c6a24ff6ce4f3816b5116a56844694 +size 2497281568 diff --git a/FluentlyQwen3-Coder-4B.Q4_K_S.gguf b/FluentlyQwen3-Coder-4B.Q4_K_S.gguf new file mode 100644 index 0000000..c91e6b7 --- /dev/null +++ b/FluentlyQwen3-Coder-4B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d226499cd433b6c52b4db4338d00915e709962116d6df3d954a152ddcc71b5e +size 2383310368 diff --git a/FluentlyQwen3-Coder-4B.Q5_K_M.gguf b/FluentlyQwen3-Coder-4B.Q5_K_M.gguf new file mode 100644 index 0000000..3331866 --- /dev/null +++ b/FluentlyQwen3-Coder-4B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e3912782d161f4f4dae59da4cc78d416f703b8d308e2452b9a25921c7092394 +size 2889514528 diff --git a/FluentlyQwen3-Coder-4B.Q5_K_S.gguf b/FluentlyQwen3-Coder-4B.Q5_K_S.gguf new file mode 100644 index 0000000..e29e6ac --- /dev/null +++ b/FluentlyQwen3-Coder-4B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76456697fa5e6bd714b3fe8f7b461c338dc767d7eb37bf455d790ba8a64c01b0 +size 2823712288 diff --git a/FluentlyQwen3-Coder-4B.Q6_K.gguf b/FluentlyQwen3-Coder-4B.Q6_K.gguf new file mode 100644 index 0000000..9f657fb --- /dev/null +++ b/FluentlyQwen3-Coder-4B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9040f3d393d713766dedfc09480efcc3304122ca5c50d59ca97b13ee08454d02 +size 3306262048 diff --git a/FluentlyQwen3-Coder-4B.Q8_0.gguf b/FluentlyQwen3-Coder-4B.Q8_0.gguf new file mode 100644 index 0000000..23363e2 --- /dev/null +++ b/FluentlyQwen3-Coder-4B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12736a8b7ae970ca9e3aa3f7089e8213ceee3b4b48e64a2d569db2c4c0b134c0 +size 4280406048 diff --git a/FluentlyQwen3-Coder-4B.f16.gguf b/FluentlyQwen3-Coder-4B.f16.gguf new file mode 100644 index 0000000..3b70558 --- /dev/null +++ b/FluentlyQwen3-Coder-4B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51d175607c3d25487a79a6f1745e74bc1971584184cd7bc55e1fa7fa9327e4d1 +size 8051286048 diff --git a/README.md b/README.md new file mode 100644 index 0000000..731237d --- /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-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/FluentlyQwen3-Coder-4B-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-GGUF/resolve/main/FluentlyQwen3-Coder-4B.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/FluentlyQwen3-Coder-4B-GGUF/resolve/main/FluentlyQwen3-Coder-4B.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/FluentlyQwen3-Coder-4B-GGUF/resolve/main/FluentlyQwen3-Coder-4B.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/FluentlyQwen3-Coder-4B-GGUF/resolve/main/FluentlyQwen3-Coder-4B.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/FluentlyQwen3-Coder-4B-GGUF/resolve/main/FluentlyQwen3-Coder-4B.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/FluentlyQwen3-Coder-4B-GGUF/resolve/main/FluentlyQwen3-Coder-4B.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/FluentlyQwen3-Coder-4B-GGUF/resolve/main/FluentlyQwen3-Coder-4B.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/FluentlyQwen3-Coder-4B-GGUF/resolve/main/FluentlyQwen3-Coder-4B.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/FluentlyQwen3-Coder-4B-GGUF/resolve/main/FluentlyQwen3-Coder-4B.Q5_K_M.gguf) | Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/FluentlyQwen3-Coder-4B-GGUF/resolve/main/FluentlyQwen3-Coder-4B.Q6_K.gguf) | Q6_K | 3.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/FluentlyQwen3-Coder-4B-GGUF/resolve/main/FluentlyQwen3-Coder-4B.Q8_0.gguf) | Q8_0 | 4.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/FluentlyQwen3-Coder-4B-GGUF/resolve/main/FluentlyQwen3-Coder-4B.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. + +