commit 4c9bc5c9d7996dff19ac7770739752b6dbd00c04 Author: ModelHub XC Date: Mon Oct 26 17:48:23 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/QWEN3-0.6B-EXTENDED-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..4e168ee --- /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-EXTENDED.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +QWEN3-0.6B-EXTENDED.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +QWEN3-0.6B-EXTENDED.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +QWEN3-0.6B-EXTENDED.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +QWEN3-0.6B-EXTENDED.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +QWEN3-0.6B-EXTENDED.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +QWEN3-0.6B-EXTENDED.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +QWEN3-0.6B-EXTENDED.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +QWEN3-0.6B-EXTENDED.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +QWEN3-0.6B-EXTENDED.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +QWEN3-0.6B-EXTENDED.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +QWEN3-0.6B-EXTENDED.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/QWEN3-0.6B-EXTENDED.IQ4_XS.gguf b/QWEN3-0.6B-EXTENDED.IQ4_XS.gguf new file mode 100644 index 0000000..dd76089 --- /dev/null +++ b/QWEN3-0.6B-EXTENDED.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:156dcb373896b17fc8996693ff01ef0a0ada8f8b28c5ea0e8b4bea23ac11301f +size 388601856 diff --git a/QWEN3-0.6B-EXTENDED.Q2_K.gguf b/QWEN3-0.6B-EXTENDED.Q2_K.gguf new file mode 100644 index 0000000..dde7b98 --- /dev/null +++ b/QWEN3-0.6B-EXTENDED.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fa63353e008896051e5eb41a8cf2828c754c777dd0aad36a0ce0832ff883413 +size 315561984 diff --git a/QWEN3-0.6B-EXTENDED.Q3_K_L.gguf b/QWEN3-0.6B-EXTENDED.Q3_K_L.gguf new file mode 100644 index 0000000..e9dba37 --- /dev/null +++ b/QWEN3-0.6B-EXTENDED.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87d6119edc05a7466034044a0a86e7174aabdc61ac2711424fa04c6584ab0500 +size 387815424 diff --git a/QWEN3-0.6B-EXTENDED.Q3_K_M.gguf b/QWEN3-0.6B-EXTENDED.Q3_K_M.gguf new file mode 100644 index 0000000..7eff3e2 --- /dev/null +++ b/QWEN3-0.6B-EXTENDED.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:780e7b7c60557462813f2686fa428fc263df21484bd7736738a48c17d14a1315 +size 366450688 diff --git a/QWEN3-0.6B-EXTENDED.Q3_K_S.gguf b/QWEN3-0.6B-EXTENDED.Q3_K_S.gguf new file mode 100644 index 0000000..ac55d82 --- /dev/null +++ b/QWEN3-0.6B-EXTENDED.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0d42a636a51ef964dbc1eaaa69ef17113deb603b95e1be17d51304f1b15c3eb +size 342398976 diff --git a/QWEN3-0.6B-EXTENDED.Q4_K_M.gguf b/QWEN3-0.6B-EXTENDED.Q4_K_M.gguf new file mode 100644 index 0000000..215edb7 --- /dev/null +++ b/QWEN3-0.6B-EXTENDED.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45c887e5de89b9ba92d4173fe11869e725035f567f33ce9baf2fed4907f27d3b +size 416028672 diff --git a/QWEN3-0.6B-EXTENDED.Q4_K_S.gguf b/QWEN3-0.6B-EXTENDED.Q4_K_S.gguf new file mode 100644 index 0000000..eebe44c --- /dev/null +++ b/QWEN3-0.6B-EXTENDED.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:661515a64f866ceb00bfb10988fdafe85538c135ff51e9ee795246489a16493e +size 402593792 diff --git a/QWEN3-0.6B-EXTENDED.Q5_K_M.gguf b/QWEN3-0.6B-EXTENDED.Q5_K_M.gguf new file mode 100644 index 0000000..d92ae31 --- /dev/null +++ b/QWEN3-0.6B-EXTENDED.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81aa702c2b14622775b61133016d27cbfc760233708da7e45d0180741ef50008 +size 463738880 diff --git a/QWEN3-0.6B-EXTENDED.Q5_K_S.gguf b/QWEN3-0.6B-EXTENDED.Q5_K_S.gguf new file mode 100644 index 0000000..c1a934d --- /dev/null +++ b/QWEN3-0.6B-EXTENDED.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e67b35e5bc545b84130957991e2db789cf5de27b59e0a022ccf883ca211f3a2 +size 455940096 diff --git a/QWEN3-0.6B-EXTENDED.Q6_K.gguf b/QWEN3-0.6B-EXTENDED.Q6_K.gguf new file mode 100644 index 0000000..35024b6 --- /dev/null +++ b/QWEN3-0.6B-EXTENDED.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0998a645155a9865409c8fc7431541de84f47a60a7ae2c5a02bcc7845703dd6e +size 514430976 diff --git a/QWEN3-0.6B-EXTENDED.Q8_0.gguf b/QWEN3-0.6B-EXTENDED.Q8_0.gguf new file mode 100644 index 0000000..6e17ba6 --- /dev/null +++ b/QWEN3-0.6B-EXTENDED.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93984bfe9c1e3f4c195111f7e55baa7d7d4958f074497e36883395b00a7ec000 +size 664341024 diff --git a/QWEN3-0.6B-EXTENDED.f16.gguf b/QWEN3-0.6B-EXTENDED.f16.gguf new file mode 100644 index 0000000..7504c0f --- /dev/null +++ b/QWEN3-0.6B-EXTENDED.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7042a5025eb0218436c701929c3364b7fb3c96178b7755b7dc562def5fc0ffb4 +size 1244637984 diff --git a/README.md b/README.md new file mode 100644 index 0000000..0b9e2b5 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: Ha-ya/QWEN3-0.6B-EXTENDED +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Ha-ya/QWEN3-0.6B-EXTENDED + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#QWEN3-0.6B-EXTENDED-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-EXTENDED-GGUF/resolve/main/QWEN3-0.6B-EXTENDED.Q2_K.gguf) | Q2_K | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/QWEN3-0.6B-EXTENDED-GGUF/resolve/main/QWEN3-0.6B-EXTENDED.Q3_K_S.gguf) | Q3_K_S | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/QWEN3-0.6B-EXTENDED-GGUF/resolve/main/QWEN3-0.6B-EXTENDED.Q3_K_M.gguf) | Q3_K_M | 0.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/QWEN3-0.6B-EXTENDED-GGUF/resolve/main/QWEN3-0.6B-EXTENDED.Q3_K_L.gguf) | Q3_K_L | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/QWEN3-0.6B-EXTENDED-GGUF/resolve/main/QWEN3-0.6B-EXTENDED.IQ4_XS.gguf) | IQ4_XS | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/QWEN3-0.6B-EXTENDED-GGUF/resolve/main/QWEN3-0.6B-EXTENDED.Q4_K_S.gguf) | Q4_K_S | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/QWEN3-0.6B-EXTENDED-GGUF/resolve/main/QWEN3-0.6B-EXTENDED.Q4_K_M.gguf) | Q4_K_M | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/QWEN3-0.6B-EXTENDED-GGUF/resolve/main/QWEN3-0.6B-EXTENDED.Q5_K_S.gguf) | Q5_K_S | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/QWEN3-0.6B-EXTENDED-GGUF/resolve/main/QWEN3-0.6B-EXTENDED.Q5_K_M.gguf) | Q5_K_M | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/QWEN3-0.6B-EXTENDED-GGUF/resolve/main/QWEN3-0.6B-EXTENDED.Q6_K.gguf) | Q6_K | 0.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/QWEN3-0.6B-EXTENDED-GGUF/resolve/main/QWEN3-0.6B-EXTENDED.Q8_0.gguf) | Q8_0 | 0.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/QWEN3-0.6B-EXTENDED-GGUF/resolve/main/QWEN3-0.6B-EXTENDED.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. + +