commit 615b0f0a525f8974350d7df463e438a754b4ecd5 Author: ModelHub XC Date: Sun Apr 12 12:11:56 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-0.6B-Pruned-0.2B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..0dcbc4c --- /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-Pruned-0.2B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Pruned-0.2B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Pruned-0.2B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Pruned-0.2B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Pruned-0.2B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Pruned-0.2B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Pruned-0.2B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Pruned-0.2B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Pruned-0.2B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Pruned-0.2B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Pruned-0.2B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Pruned-0.2B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-0.6B-Pruned-0.2B.IQ4_XS.gguf b/Qwen3-0.6B-Pruned-0.2B.IQ4_XS.gguf new file mode 100644 index 0000000..ce88657 --- /dev/null +++ b/Qwen3-0.6B-Pruned-0.2B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a01dd5b48a93a292ec3ea01bd7961a629052b131da37cecf68b8e1ba1feb21f6 +size 150295712 diff --git a/Qwen3-0.6B-Pruned-0.2B.Q2_K.gguf b/Qwen3-0.6B-Pruned-0.2B.Q2_K.gguf new file mode 100644 index 0000000..2c21a8f --- /dev/null +++ b/Qwen3-0.6B-Pruned-0.2B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ceca6124948348fc729b3f26efb559a75c19bd33591a535d317e1cbe96cc53c +size 145183904 diff --git a/Qwen3-0.6B-Pruned-0.2B.Q3_K_L.gguf b/Qwen3-0.6B-Pruned-0.2B.Q3_K_L.gguf new file mode 100644 index 0000000..578171b --- /dev/null +++ b/Qwen3-0.6B-Pruned-0.2B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e79339e9076a0d171d9a2adfd3ffacb56f9cc03e5a7ac1b11152ec05f0dd098 +size 150344864 diff --git a/Qwen3-0.6B-Pruned-0.2B.Q3_K_M.gguf b/Qwen3-0.6B-Pruned-0.2B.Q3_K_M.gguf new file mode 100644 index 0000000..675b3de --- /dev/null +++ b/Qwen3-0.6B-Pruned-0.2B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:397cd3b5cecec754d308507a4fad6a0c1e76e0ef56a89dedfe9fbfdcaa64cf27 +size 149034144 diff --git a/Qwen3-0.6B-Pruned-0.2B.Q3_K_S.gguf b/Qwen3-0.6B-Pruned-0.2B.Q3_K_S.gguf new file mode 100644 index 0000000..391c44d --- /dev/null +++ b/Qwen3-0.6B-Pruned-0.2B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdc147eee0335ee290864e2d9e8ef2efa88068d3bcec058b62f790fabe0812d1 +size 147100832 diff --git a/Qwen3-0.6B-Pruned-0.2B.Q4_K_M.gguf b/Qwen3-0.6B-Pruned-0.2B.Q4_K_M.gguf new file mode 100644 index 0000000..d2cbb2e --- /dev/null +++ b/Qwen3-0.6B-Pruned-0.2B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c7f720cd4ac2b5a0553709c64c6a34d96164e7d74aaa819fa048d5d4add9348 +size 152360096 diff --git a/Qwen3-0.6B-Pruned-0.2B.Q4_K_S.gguf b/Qwen3-0.6B-Pruned-0.2B.Q4_K_S.gguf new file mode 100644 index 0000000..dd84bd0 --- /dev/null +++ b/Qwen3-0.6B-Pruned-0.2B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b57b3c5e0d04d4995b6fbe6ce86242d5bcd2dbe86992b0f0492a356a0630e0c +size 151540896 diff --git a/Qwen3-0.6B-Pruned-0.2B.Q5_K_M.gguf b/Qwen3-0.6B-Pruned-0.2B.Q5_K_M.gguf new file mode 100644 index 0000000..ad1ffff --- /dev/null +++ b/Qwen3-0.6B-Pruned-0.2B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8a506eb20edfadeb3426286933df6aae3375c0e79992415fb7871763a9c53ac +size 155767968 diff --git a/Qwen3-0.6B-Pruned-0.2B.Q5_K_S.gguf b/Qwen3-0.6B-Pruned-0.2B.Q5_K_S.gguf new file mode 100644 index 0000000..40d110a --- /dev/null +++ b/Qwen3-0.6B-Pruned-0.2B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3356175f0b6ad36f464a908a199aa547308f18f5fb860d28ed7d861c1a540c45 +size 155210912 diff --git a/Qwen3-0.6B-Pruned-0.2B.Q6_K.gguf b/Qwen3-0.6B-Pruned-0.2B.Q6_K.gguf new file mode 100644 index 0000000..2abffce --- /dev/null +++ b/Qwen3-0.6B-Pruned-0.2B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff1d6654799f907f87aedcfda3b5cd1a78f3c79e7b6145f2e93d83abd8b8e323 +size 159388832 diff --git a/Qwen3-0.6B-Pruned-0.2B.Q8_0.gguf b/Qwen3-0.6B-Pruned-0.2B.Q8_0.gguf new file mode 100644 index 0000000..b0ea2f8 --- /dev/null +++ b/Qwen3-0.6B-Pruned-0.2B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad1fe706700490385936e87f6f3514f67788cbccd8cc143c042f5517c06561f1 +size 204687520 diff --git a/Qwen3-0.6B-Pruned-0.2B.f16.gguf b/Qwen3-0.6B-Pruned-0.2B.f16.gguf new file mode 100644 index 0000000..676aa1e --- /dev/null +++ b/Qwen3-0.6B-Pruned-0.2B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8e692f429d59ce320a13ada8cb3efb673447eee3c3b12b27eddb469e9424cc1 +size 380037280 diff --git a/README.md b/README.md new file mode 100644 index 0000000..d7f74d2 --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: ubicloud/Qwen3-0.6B-Pruned-0.2B +language: +- en +library_name: transformers +license: mit +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- pruned +--- +## About + + + + + + + + + +static quants of https://huggingface.co/ubicloud/Qwen3-0.6B-Pruned-0.2B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-0.6B-Pruned-0.2B-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-Pruned-0.2B-GGUF/resolve/main/Qwen3-0.6B-Pruned-0.2B.Q2_K.gguf) | Q2_K | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Pruned-0.2B-GGUF/resolve/main/Qwen3-0.6B-Pruned-0.2B.Q3_K_S.gguf) | Q3_K_S | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Pruned-0.2B-GGUF/resolve/main/Qwen3-0.6B-Pruned-0.2B.Q3_K_M.gguf) | Q3_K_M | 0.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Pruned-0.2B-GGUF/resolve/main/Qwen3-0.6B-Pruned-0.2B.IQ4_XS.gguf) | IQ4_XS | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Pruned-0.2B-GGUF/resolve/main/Qwen3-0.6B-Pruned-0.2B.Q3_K_L.gguf) | Q3_K_L | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Pruned-0.2B-GGUF/resolve/main/Qwen3-0.6B-Pruned-0.2B.Q4_K_S.gguf) | Q4_K_S | 0.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Pruned-0.2B-GGUF/resolve/main/Qwen3-0.6B-Pruned-0.2B.Q4_K_M.gguf) | Q4_K_M | 0.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Pruned-0.2B-GGUF/resolve/main/Qwen3-0.6B-Pruned-0.2B.Q5_K_S.gguf) | Q5_K_S | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Pruned-0.2B-GGUF/resolve/main/Qwen3-0.6B-Pruned-0.2B.Q5_K_M.gguf) | Q5_K_M | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Pruned-0.2B-GGUF/resolve/main/Qwen3-0.6B-Pruned-0.2B.Q6_K.gguf) | Q6_K | 0.3 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Pruned-0.2B-GGUF/resolve/main/Qwen3-0.6B-Pruned-0.2B.Q8_0.gguf) | Q8_0 | 0.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Pruned-0.2B-GGUF/resolve/main/Qwen3-0.6B-Pruned-0.2B.f16.gguf) | f16 | 0.5 | 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. + +