commit 4286055bb3f7b004e8666a1c41c4faafa4bacd6e Author: ModelHub XC Date: Sun Sep 6 20:03:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/qwen3-4b-ko-writing-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d628e45 --- /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 +qwen3-4b-ko-writing.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +qwen3-4b-ko-writing.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +qwen3-4b-ko-writing.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +qwen3-4b-ko-writing.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +qwen3-4b-ko-writing.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +qwen3-4b-ko-writing.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +qwen3-4b-ko-writing.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +qwen3-4b-ko-writing.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +qwen3-4b-ko-writing.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +qwen3-4b-ko-writing.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +qwen3-4b-ko-writing.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +qwen3-4b-ko-writing.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..1a2b34e --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: sophie1738/qwen3-4b-ko-writing +language: +- ko +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/sophie1738/qwen3-4b-ko-writing + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#qwen3-4b-ko-writing-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/qwen3-4b-ko-writing-GGUF/resolve/main/qwen3-4b-ko-writing.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/qwen3-4b-ko-writing-GGUF/resolve/main/qwen3-4b-ko-writing.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/qwen3-4b-ko-writing-GGUF/resolve/main/qwen3-4b-ko-writing.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/qwen3-4b-ko-writing-GGUF/resolve/main/qwen3-4b-ko-writing.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/qwen3-4b-ko-writing-GGUF/resolve/main/qwen3-4b-ko-writing.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/qwen3-4b-ko-writing-GGUF/resolve/main/qwen3-4b-ko-writing.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/qwen3-4b-ko-writing-GGUF/resolve/main/qwen3-4b-ko-writing.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/qwen3-4b-ko-writing-GGUF/resolve/main/qwen3-4b-ko-writing.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/qwen3-4b-ko-writing-GGUF/resolve/main/qwen3-4b-ko-writing.Q5_K_M.gguf) | Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/qwen3-4b-ko-writing-GGUF/resolve/main/qwen3-4b-ko-writing.Q6_K.gguf) | Q6_K | 3.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/qwen3-4b-ko-writing-GGUF/resolve/main/qwen3-4b-ko-writing.Q8_0.gguf) | Q8_0 | 4.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/qwen3-4b-ko-writing-GGUF/resolve/main/qwen3-4b-ko-writing.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. + + diff --git a/qwen3-4b-ko-writing.IQ4_XS.gguf b/qwen3-4b-ko-writing.IQ4_XS.gguf new file mode 100644 index 0000000..bad44d6 --- /dev/null +++ b/qwen3-4b-ko-writing.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67ee60395a5728e7e72836b401245666967214730a0655e0b197ae69f4fbb652 +size 2286315232 diff --git a/qwen3-4b-ko-writing.Q2_K.gguf b/qwen3-4b-ko-writing.Q2_K.gguf new file mode 100644 index 0000000..027a8a4 --- /dev/null +++ b/qwen3-4b-ko-writing.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f51ad8255d726073bff5931f56e1fff5fcbf29164037dd307e6f3ec07eb68753 +size 1669498592 diff --git a/qwen3-4b-ko-writing.Q3_K_L.gguf b/qwen3-4b-ko-writing.Q3_K_L.gguf new file mode 100644 index 0000000..cdc29a2 --- /dev/null +++ b/qwen3-4b-ko-writing.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84559ee9d6c0c219406b7c2b15b0a7fbede116001e918a5fd22c30b40d4f0def +size 2239784672 diff --git a/qwen3-4b-ko-writing.Q3_K_M.gguf b/qwen3-4b-ko-writing.Q3_K_M.gguf new file mode 100644 index 0000000..a1b3842 --- /dev/null +++ b/qwen3-4b-ko-writing.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33463b2d82664c25cdfc8d7acb2328fed7eef48a77d00e93ca561486478d1f4e +size 2075616992 diff --git a/qwen3-4b-ko-writing.Q3_K_S.gguf b/qwen3-4b-ko-writing.Q3_K_S.gguf new file mode 100644 index 0000000..192f1ab --- /dev/null +++ b/qwen3-4b-ko-writing.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c26ff93e0cee88c36a32493bbb07dd2521252431018e72153851f5a412382c1e +size 1886996192 diff --git a/qwen3-4b-ko-writing.Q4_K_M.gguf b/qwen3-4b-ko-writing.Q4_K_M.gguf new file mode 100644 index 0000000..6116b66 --- /dev/null +++ b/qwen3-4b-ko-writing.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c4fe9358991b4484c347d30f22c709e155c6ce344351c5b1a7baa1a4790f0f7 +size 2497279712 diff --git a/qwen3-4b-ko-writing.Q4_K_S.gguf b/qwen3-4b-ko-writing.Q4_K_S.gguf new file mode 100644 index 0000000..443c4c9 --- /dev/null +++ b/qwen3-4b-ko-writing.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98d24723772a9624be69205c02a2cac525f05cb7cb13972656b0c239e206be54 +size 2383308512 diff --git a/qwen3-4b-ko-writing.Q5_K_M.gguf b/qwen3-4b-ko-writing.Q5_K_M.gguf new file mode 100644 index 0000000..9529e50 --- /dev/null +++ b/qwen3-4b-ko-writing.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1c7d44bd9e608cfdbd38c27bce0fbd41018790336f0278466db9986ec7c4c63 +size 2889512672 diff --git a/qwen3-4b-ko-writing.Q5_K_S.gguf b/qwen3-4b-ko-writing.Q5_K_S.gguf new file mode 100644 index 0000000..74c8b60 --- /dev/null +++ b/qwen3-4b-ko-writing.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15e875789db93effc5ad4ab920f104438a54537438a692697d1c138f4596b774 +size 2823710432 diff --git a/qwen3-4b-ko-writing.Q6_K.gguf b/qwen3-4b-ko-writing.Q6_K.gguf new file mode 100644 index 0000000..9157b16 --- /dev/null +++ b/qwen3-4b-ko-writing.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1ec8fdaa04f92a586853e5b15645c209aa18597cd090a5c91bbf92c6e806e45 +size 3306260192 diff --git a/qwen3-4b-ko-writing.Q8_0.gguf b/qwen3-4b-ko-writing.Q8_0.gguf new file mode 100644 index 0000000..463152f --- /dev/null +++ b/qwen3-4b-ko-writing.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54c29891d41c4f2c573e07b227f50ab4f0f48cbb7f458d5701cb0d44bee2dd65 +size 4280404192 diff --git a/qwen3-4b-ko-writing.f16.gguf b/qwen3-4b-ko-writing.f16.gguf new file mode 100644 index 0000000..2ca16da --- /dev/null +++ b/qwen3-4b-ko-writing.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10df3fd2cff76a7ffcbc09a8c55d16416c1a6d319b7b108456b560e22110c236 +size 8051284192