commit 47ed6cf97bdb8a01dd9b9c5e57afe30a55b67dc7 Author: ModelHub XC Date: Tue Aug 25 11:58:35 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/SML-model-Qwen3-0.6B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2f42236 --- /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 +SML-model-Qwen3-0.6B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +SML-model-Qwen3-0.6B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +SML-model-Qwen3-0.6B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +SML-model-Qwen3-0.6B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SML-model-Qwen3-0.6B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SML-model-Qwen3-0.6B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SML-model-Qwen3-0.6B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SML-model-Qwen3-0.6B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SML-model-Qwen3-0.6B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SML-model-Qwen3-0.6B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +SML-model-Qwen3-0.6B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +SML-model-Qwen3-0.6B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..4315b80 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: minhquy1624/SML-model-Qwen3-0.6B +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + + + + +static quants of https://huggingface.co/minhquy1624/SML-model-Qwen3-0.6B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#SML-model-Qwen3-0.6B-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/SML-model-Qwen3-0.6B-GGUF/resolve/main/SML-model-Qwen3-0.6B.Q2_K.gguf) | Q2_K | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/SML-model-Qwen3-0.6B-GGUF/resolve/main/SML-model-Qwen3-0.6B.Q3_K_S.gguf) | Q3_K_S | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/SML-model-Qwen3-0.6B-GGUF/resolve/main/SML-model-Qwen3-0.6B.Q3_K_M.gguf) | Q3_K_M | 0.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/SML-model-Qwen3-0.6B-GGUF/resolve/main/SML-model-Qwen3-0.6B.Q3_K_L.gguf) | Q3_K_L | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/SML-model-Qwen3-0.6B-GGUF/resolve/main/SML-model-Qwen3-0.6B.IQ4_XS.gguf) | IQ4_XS | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/SML-model-Qwen3-0.6B-GGUF/resolve/main/SML-model-Qwen3-0.6B.Q4_K_S.gguf) | Q4_K_S | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/SML-model-Qwen3-0.6B-GGUF/resolve/main/SML-model-Qwen3-0.6B.Q4_K_M.gguf) | Q4_K_M | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/SML-model-Qwen3-0.6B-GGUF/resolve/main/SML-model-Qwen3-0.6B.Q5_K_S.gguf) | Q5_K_S | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/SML-model-Qwen3-0.6B-GGUF/resolve/main/SML-model-Qwen3-0.6B.Q5_K_M.gguf) | Q5_K_M | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/SML-model-Qwen3-0.6B-GGUF/resolve/main/SML-model-Qwen3-0.6B.Q6_K.gguf) | Q6_K | 0.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/SML-model-Qwen3-0.6B-GGUF/resolve/main/SML-model-Qwen3-0.6B.Q8_0.gguf) | Q8_0 | 0.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/SML-model-Qwen3-0.6B-GGUF/resolve/main/SML-model-Qwen3-0.6B.f16.gguf) | f16 | 1.3 | 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. + + diff --git a/SML-model-Qwen3-0.6B.IQ4_XS.gguf b/SML-model-Qwen3-0.6B.IQ4_XS.gguf new file mode 100644 index 0000000..6efde64 --- /dev/null +++ b/SML-model-Qwen3-0.6B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc7bb16645ef81dfe53f4a8e63be32416dc578ebb48cac577334759111edb503 +size 369278208 diff --git a/SML-model-Qwen3-0.6B.Q2_K.gguf b/SML-model-Qwen3-0.6B.Q2_K.gguf new file mode 100644 index 0000000..1956462 --- /dev/null +++ b/SML-model-Qwen3-0.6B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:512f87ac848d149e8a245263624dac34053806468c17df434bf057be4fab150b +size 296238336 diff --git a/SML-model-Qwen3-0.6B.Q3_K_L.gguf b/SML-model-Qwen3-0.6B.Q3_K_L.gguf new file mode 100644 index 0000000..909041e --- /dev/null +++ b/SML-model-Qwen3-0.6B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13f1e41ca61909001f1475334ac668bc56336b5eb48e47c29370e247667d09ef +size 368491776 diff --git a/SML-model-Qwen3-0.6B.Q3_K_M.gguf b/SML-model-Qwen3-0.6B.Q3_K_M.gguf new file mode 100644 index 0000000..8fa3922 --- /dev/null +++ b/SML-model-Qwen3-0.6B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b01e15429368d8764628d7cb0c90cc47b01289f1f757633bf864d1e95edaacf7 +size 347127040 diff --git a/SML-model-Qwen3-0.6B.Q3_K_S.gguf b/SML-model-Qwen3-0.6B.Q3_K_S.gguf new file mode 100644 index 0000000..f64dd6c --- /dev/null +++ b/SML-model-Qwen3-0.6B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa4b54eb4b8a950f51dd3829f7a1abe162e033218625879da0ea209aec0feb2d +size 323075328 diff --git a/SML-model-Qwen3-0.6B.Q4_K_M.gguf b/SML-model-Qwen3-0.6B.Q4_K_M.gguf new file mode 100644 index 0000000..7730bfc --- /dev/null +++ b/SML-model-Qwen3-0.6B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18d09ff285704c456aecdf27e74e830a9db5d8e7c78460705e0d6c58d3b6d6af +size 396705024 diff --git a/SML-model-Qwen3-0.6B.Q4_K_S.gguf b/SML-model-Qwen3-0.6B.Q4_K_S.gguf new file mode 100644 index 0000000..b65c5a4 --- /dev/null +++ b/SML-model-Qwen3-0.6B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a3f4ca4a9c4d02e21e50eeaff98af985eb71dc46521c4a20672a9424d0c2c93 +size 383270144 diff --git a/SML-model-Qwen3-0.6B.Q5_K_M.gguf b/SML-model-Qwen3-0.6B.Q5_K_M.gguf new file mode 100644 index 0000000..3cf7dcb --- /dev/null +++ b/SML-model-Qwen3-0.6B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd3349161cf39f09225d76e5202a52fb2f3ad06598af48f7cec582e20d0241ce +size 444415232 diff --git a/SML-model-Qwen3-0.6B.Q5_K_S.gguf b/SML-model-Qwen3-0.6B.Q5_K_S.gguf new file mode 100644 index 0000000..25765c4 --- /dev/null +++ b/SML-model-Qwen3-0.6B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:acf1cadb2e329e475776765840d7841b7cdced5707bbe21b460d2b600559e4ca +size 436616448 diff --git a/SML-model-Qwen3-0.6B.Q6_K.gguf b/SML-model-Qwen3-0.6B.Q6_K.gguf new file mode 100644 index 0000000..bb0b326 --- /dev/null +++ b/SML-model-Qwen3-0.6B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a186abb74985d8b7c2cf4488fcdc4b5bd74277934882f94f01af057f8f2b8b0e +size 495107328 diff --git a/SML-model-Qwen3-0.6B.Q8_0.gguf b/SML-model-Qwen3-0.6B.Q8_0.gguf new file mode 100644 index 0000000..e5accb2 --- /dev/null +++ b/SML-model-Qwen3-0.6B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ef1b2bd8130bae311c9e734a7cad65244cda77673b8e79acfd267d0d0d5c665 +size 639447296 diff --git a/SML-model-Qwen3-0.6B.f16.gguf b/SML-model-Qwen3-0.6B.f16.gguf new file mode 100644 index 0000000..ed76c28 --- /dev/null +++ b/SML-model-Qwen3-0.6B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:827ef936dab96d3ba545d3d92085b1cb9b5daea2b5d1f9f1d6bc0fb605279316 +size 1198182656