commit 4323427190fe6891083ea0c6175f0975e5a96ee9 Author: ModelHub XC Date: Thu Jul 23 07:03:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-0.6B-Full-Finetuning-Thinking-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..3e74708 --- /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 +Qwen3-0.6B-Full-Finetuning-Thinking.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Full-Finetuning-Thinking.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Full-Finetuning-Thinking.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Full-Finetuning-Thinking.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Full-Finetuning-Thinking.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Full-Finetuning-Thinking.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Full-Finetuning-Thinking.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Full-Finetuning-Thinking.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Full-Finetuning-Thinking.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Full-Finetuning-Thinking.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Full-Finetuning-Thinking.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Full-Finetuning-Thinking.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-0.6B-Full-Finetuning-Thinking.IQ4_XS.gguf b/Qwen3-0.6B-Full-Finetuning-Thinking.IQ4_XS.gguf new file mode 100644 index 0000000..122b79f --- /dev/null +++ b/Qwen3-0.6B-Full-Finetuning-Thinking.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14472f72a85708ba836827474ccc293d5be6bd233fd17584b4c24d94a07a56fe +size 369279008 diff --git a/Qwen3-0.6B-Full-Finetuning-Thinking.Q2_K.gguf b/Qwen3-0.6B-Full-Finetuning-Thinking.Q2_K.gguf new file mode 100644 index 0000000..5dd2267 --- /dev/null +++ b/Qwen3-0.6B-Full-Finetuning-Thinking.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c7254710c56a630e48163b7bd4bdce5cc4c9ff11605761db85737ce4846c9a2 +size 296239136 diff --git a/Qwen3-0.6B-Full-Finetuning-Thinking.Q3_K_L.gguf b/Qwen3-0.6B-Full-Finetuning-Thinking.Q3_K_L.gguf new file mode 100644 index 0000000..4af4cf4 --- /dev/null +++ b/Qwen3-0.6B-Full-Finetuning-Thinking.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3ebbdd36a2656a001ee4c797e05b25edeeb531290e12ab6bb55ad0e5172de84 +size 368492576 diff --git a/Qwen3-0.6B-Full-Finetuning-Thinking.Q3_K_M.gguf b/Qwen3-0.6B-Full-Finetuning-Thinking.Q3_K_M.gguf new file mode 100644 index 0000000..f910f82 --- /dev/null +++ b/Qwen3-0.6B-Full-Finetuning-Thinking.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95dc0e8dbce2add449b3dede01edf4b51ccfdf23b8e832b76333ffe72e27d9b7 +size 347127840 diff --git a/Qwen3-0.6B-Full-Finetuning-Thinking.Q3_K_S.gguf b/Qwen3-0.6B-Full-Finetuning-Thinking.Q3_K_S.gguf new file mode 100644 index 0000000..5d504ff --- /dev/null +++ b/Qwen3-0.6B-Full-Finetuning-Thinking.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e37c4511dc407a64693a0936ca29d535a30badd9dbd1d7cf15edca76d6e8c776 +size 323076128 diff --git a/Qwen3-0.6B-Full-Finetuning-Thinking.Q4_K_M.gguf b/Qwen3-0.6B-Full-Finetuning-Thinking.Q4_K_M.gguf new file mode 100644 index 0000000..aabfbc6 --- /dev/null +++ b/Qwen3-0.6B-Full-Finetuning-Thinking.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c99f3897ccca7df645972a2fe5c37b280da9be30d7a4f0dfcb01ff5886efdd15 +size 396705824 diff --git a/Qwen3-0.6B-Full-Finetuning-Thinking.Q4_K_S.gguf b/Qwen3-0.6B-Full-Finetuning-Thinking.Q4_K_S.gguf new file mode 100644 index 0000000..3816eb2 --- /dev/null +++ b/Qwen3-0.6B-Full-Finetuning-Thinking.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:925b50dea4a32f33270e14356787f92b39cd7db24b42c0700154f8c1dbb19c94 +size 383270944 diff --git a/Qwen3-0.6B-Full-Finetuning-Thinking.Q5_K_M.gguf b/Qwen3-0.6B-Full-Finetuning-Thinking.Q5_K_M.gguf new file mode 100644 index 0000000..82e44ec --- /dev/null +++ b/Qwen3-0.6B-Full-Finetuning-Thinking.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24adb2aa11ed12202725eaf348f55f424eeae043274b8a07af6160d5a6e1ee11 +size 444416032 diff --git a/Qwen3-0.6B-Full-Finetuning-Thinking.Q5_K_S.gguf b/Qwen3-0.6B-Full-Finetuning-Thinking.Q5_K_S.gguf new file mode 100644 index 0000000..77784f3 --- /dev/null +++ b/Qwen3-0.6B-Full-Finetuning-Thinking.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ce27125d2b279e4cf03e184abcaa59e901ec212da3b0baf10af9d364ff7a385 +size 436617248 diff --git a/Qwen3-0.6B-Full-Finetuning-Thinking.Q6_K.gguf b/Qwen3-0.6B-Full-Finetuning-Thinking.Q6_K.gguf new file mode 100644 index 0000000..056e436 --- /dev/null +++ b/Qwen3-0.6B-Full-Finetuning-Thinking.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7073578a6f8be3664c4005f51c294486b2099b8d3257efc8cd9fddf93ed50544 +size 495108128 diff --git a/Qwen3-0.6B-Full-Finetuning-Thinking.Q8_0.gguf b/Qwen3-0.6B-Full-Finetuning-Thinking.Q8_0.gguf new file mode 100644 index 0000000..4550161 --- /dev/null +++ b/Qwen3-0.6B-Full-Finetuning-Thinking.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:495fa8742ce08f9eec032d560b71fbc3ad49b9afa85b63157dc577ccb2001305 +size 639448096 diff --git a/Qwen3-0.6B-Full-Finetuning-Thinking.f16.gguf b/Qwen3-0.6B-Full-Finetuning-Thinking.f16.gguf new file mode 100644 index 0000000..b6dfb02 --- /dev/null +++ b/Qwen3-0.6B-Full-Finetuning-Thinking.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aff7aa4b814bb883178e2cc8e0617b23c912633ccf0e38f5786da7f646622eaf +size 1198183456 diff --git a/README.md b/README.md new file mode 100644 index 0000000..7b9e0f2 --- /dev/null +++ b/README.md @@ -0,0 +1,75 @@ +--- +base_model: mkubaszek/Qwen3-0.6B-Full-Finetuning-Thinking +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- unsloth +- trl +- sft +--- +## About + + + + + + + + + +static quants of https://huggingface.co/mkubaszek/Qwen3-0.6B-Full-Finetuning-Thinking + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-0.6B-Full-Finetuning-Thinking-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/Qwen3-0.6B-Full-Finetuning-Thinking-GGUF/resolve/main/Qwen3-0.6B-Full-Finetuning-Thinking.Q2_K.gguf) | Q2_K | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Full-Finetuning-Thinking-GGUF/resolve/main/Qwen3-0.6B-Full-Finetuning-Thinking.Q3_K_S.gguf) | Q3_K_S | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Full-Finetuning-Thinking-GGUF/resolve/main/Qwen3-0.6B-Full-Finetuning-Thinking.Q3_K_M.gguf) | Q3_K_M | 0.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Full-Finetuning-Thinking-GGUF/resolve/main/Qwen3-0.6B-Full-Finetuning-Thinking.Q3_K_L.gguf) | Q3_K_L | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Full-Finetuning-Thinking-GGUF/resolve/main/Qwen3-0.6B-Full-Finetuning-Thinking.IQ4_XS.gguf) | IQ4_XS | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Full-Finetuning-Thinking-GGUF/resolve/main/Qwen3-0.6B-Full-Finetuning-Thinking.Q4_K_S.gguf) | Q4_K_S | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Full-Finetuning-Thinking-GGUF/resolve/main/Qwen3-0.6B-Full-Finetuning-Thinking.Q4_K_M.gguf) | Q4_K_M | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Full-Finetuning-Thinking-GGUF/resolve/main/Qwen3-0.6B-Full-Finetuning-Thinking.Q5_K_S.gguf) | Q5_K_S | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Full-Finetuning-Thinking-GGUF/resolve/main/Qwen3-0.6B-Full-Finetuning-Thinking.Q5_K_M.gguf) | Q5_K_M | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Full-Finetuning-Thinking-GGUF/resolve/main/Qwen3-0.6B-Full-Finetuning-Thinking.Q6_K.gguf) | Q6_K | 0.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Full-Finetuning-Thinking-GGUF/resolve/main/Qwen3-0.6B-Full-Finetuning-Thinking.Q8_0.gguf) | Q8_0 | 0.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Full-Finetuning-Thinking-GGUF/resolve/main/Qwen3-0.6B-Full-Finetuning-Thinking.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. + +