commit c84c167e40a9afe8b1814c4e63d091945c3e0780 Author: ModelHub XC Date: Sun Apr 12 06:19:54 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-tiny-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..6136fc0 --- /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-tiny.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-tiny.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-tiny.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-tiny.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-tiny.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-tiny.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-tiny.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-tiny.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-tiny.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-tiny.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-tiny.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-tiny.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-tiny.IQ4_XS.gguf b/Qwen3-tiny.IQ4_XS.gguf new file mode 100644 index 0000000..4238b03 --- /dev/null +++ b/Qwen3-tiny.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5bcf01b7a0c0fb55a6b5d810217ea66c2142e935fd27718be5c49e33a5cc4f04 +size 232948448 diff --git a/Qwen3-tiny.Q2_K.gguf b/Qwen3-tiny.Q2_K.gguf new file mode 100644 index 0000000..1def958 --- /dev/null +++ b/Qwen3-tiny.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:457d1195796c41c6a066f9f3d6db72aa869f049c2522cbc4f1618797083a797e +size 196233952 diff --git a/Qwen3-tiny.Q3_K_L.gguf b/Qwen3-tiny.Q3_K_L.gguf new file mode 100644 index 0000000..a48e0a3 --- /dev/null +++ b/Qwen3-tiny.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4985a4e1c0a5371f45df9a82a817ce5b787ed0fda55ab7692346aeed8d624898 +size 217196256 diff --git a/Qwen3-tiny.Q3_K_M.gguf b/Qwen3-tiny.Q3_K_M.gguf new file mode 100644 index 0000000..aadba6f --- /dev/null +++ b/Qwen3-tiny.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91bc10ca5ef66cc08b3a0c2791c00a79155bc36ec536d3aed84b0afd71d9e976 +size 215885536 diff --git a/Qwen3-tiny.Q3_K_S.gguf b/Qwen3-tiny.Q3_K_S.gguf new file mode 100644 index 0000000..f97d690 --- /dev/null +++ b/Qwen3-tiny.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82b7fb0028df9463762e08885626d2a43ff4ac9862153f2f2460c04bba9a6195 +size 213952224 diff --git a/Qwen3-tiny.Q4_K_M.gguf b/Qwen3-tiny.Q4_K_M.gguf new file mode 100644 index 0000000..6bdd4de --- /dev/null +++ b/Qwen3-tiny.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eae110542d3ba13380b7f47d3fb37ca69c6a2535ac2e0c6bbfd88eac4a52a0f2 +size 239874784 diff --git a/Qwen3-tiny.Q4_K_S.gguf b/Qwen3-tiny.Q4_K_S.gguf new file mode 100644 index 0000000..2ccb469 --- /dev/null +++ b/Qwen3-tiny.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a85f20862a20aacfdc663507c7029acf2c5f6a7678af03d683281c99f339dae +size 239055584 diff --git a/Qwen3-tiny.Q5_K_M.gguf b/Qwen3-tiny.Q5_K_M.gguf new file mode 100644 index 0000000..8b83ecf --- /dev/null +++ b/Qwen3-tiny.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8aecf5d0669cd42b631b2ee1173e19442f3ba607c443fb2ff0eca1fa46d49846 +size 262730464 diff --git a/Qwen3-tiny.Q5_K_S.gguf b/Qwen3-tiny.Q5_K_S.gguf new file mode 100644 index 0000000..2370241 --- /dev/null +++ b/Qwen3-tiny.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e19a2694e0d75d8df53d557a9eb8bbcc39ca3d432549477df4ec65386d5c8c17 +size 262173408 diff --git a/Qwen3-tiny.Q6_K.gguf b/Qwen3-tiny.Q6_K.gguf new file mode 100644 index 0000000..e87d7dd --- /dev/null +++ b/Qwen3-tiny.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da80cc70d59ba6c32bf8f099794dc5bc617e3d546d6bd0576a99b3b484674480 +size 287014624 diff --git a/Qwen3-tiny.Q8_0.gguf b/Qwen3-tiny.Q8_0.gguf new file mode 100644 index 0000000..fd278e1 --- /dev/null +++ b/Qwen3-tiny.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26ff5638cfc8aa9f24cdba8f5df595a3f17446089eebd22824a61ec47b6c0d21 +size 369993440 diff --git a/Qwen3-tiny.f16.gguf b/Qwen3-tiny.f16.gguf new file mode 100644 index 0000000..2a0ded5 --- /dev/null +++ b/Qwen3-tiny.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2963af75782a522bc8595818e57812e6a7ae61145762454eb380f1dfd73bf04 +size 691201760 diff --git a/README.md b/README.md new file mode 100644 index 0000000..5991839 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: DecoderImmortal/Qwen3-tiny +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/DecoderImmortal/Qwen3-tiny + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-tiny-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-tiny-GGUF/resolve/main/Qwen3-tiny.Q2_K.gguf) | Q2_K | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-tiny-GGUF/resolve/main/Qwen3-tiny.Q3_K_S.gguf) | Q3_K_S | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-tiny-GGUF/resolve/main/Qwen3-tiny.Q3_K_M.gguf) | Q3_K_M | 0.3 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-tiny-GGUF/resolve/main/Qwen3-tiny.Q3_K_L.gguf) | Q3_K_L | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-tiny-GGUF/resolve/main/Qwen3-tiny.IQ4_XS.gguf) | IQ4_XS | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-tiny-GGUF/resolve/main/Qwen3-tiny.Q4_K_S.gguf) | Q4_K_S | 0.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-tiny-GGUF/resolve/main/Qwen3-tiny.Q4_K_M.gguf) | Q4_K_M | 0.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-tiny-GGUF/resolve/main/Qwen3-tiny.Q5_K_S.gguf) | Q5_K_S | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-tiny-GGUF/resolve/main/Qwen3-tiny.Q5_K_M.gguf) | Q5_K_M | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-tiny-GGUF/resolve/main/Qwen3-tiny.Q6_K.gguf) | Q6_K | 0.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-tiny-GGUF/resolve/main/Qwen3-tiny.Q8_0.gguf) | Q8_0 | 0.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-tiny-GGUF/resolve/main/Qwen3-tiny.f16.gguf) | f16 | 0.8 | 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. + +