commit 6d370c353620a14551eaa4c8d0603a921c980491 Author: ModelHub XC Date: Mon Jul 20 03:53:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-0.6B-Base-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..47a4ad4 --- /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-Base.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Base.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Base.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Base.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Base.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Base.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Base.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Base.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Base.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Base.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Base.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Base.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-0.6B-Base.IQ4_XS.gguf b/Qwen3-0.6B-Base.IQ4_XS.gguf new file mode 100644 index 0000000..16c31f8 --- /dev/null +++ b/Qwen3-0.6B-Base.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ac59732046acd63dfe74050e76946f686e1b2580dcf8de01c2a387b3efc5b84 +size 369278144 diff --git a/Qwen3-0.6B-Base.Q2_K.gguf b/Qwen3-0.6B-Base.Q2_K.gguf new file mode 100644 index 0000000..de5b516 --- /dev/null +++ b/Qwen3-0.6B-Base.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:629447b2284e62ed8704e71d8b69e8b853726f391ed5b4831c91fe4ceb890eb0 +size 296238272 diff --git a/Qwen3-0.6B-Base.Q3_K_L.gguf b/Qwen3-0.6B-Base.Q3_K_L.gguf new file mode 100644 index 0000000..0cb675d --- /dev/null +++ b/Qwen3-0.6B-Base.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2fadb78d2688d041d771eff9326079db7af80c838f3ac1f29c193eb591495ab +size 368491712 diff --git a/Qwen3-0.6B-Base.Q3_K_M.gguf b/Qwen3-0.6B-Base.Q3_K_M.gguf new file mode 100644 index 0000000..a6abacf --- /dev/null +++ b/Qwen3-0.6B-Base.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d86b1532692cf02ead648f957e3e77832a62a9e423f89a5cb269dcb81673ef15 +size 347126976 diff --git a/Qwen3-0.6B-Base.Q3_K_S.gguf b/Qwen3-0.6B-Base.Q3_K_S.gguf new file mode 100644 index 0000000..c48f2b3 --- /dev/null +++ b/Qwen3-0.6B-Base.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9e088a41311dc5361e3d3a05d523ff07c29d58f23dbb7ce201f829f12737207 +size 323075264 diff --git a/Qwen3-0.6B-Base.Q4_K_M.gguf b/Qwen3-0.6B-Base.Q4_K_M.gguf new file mode 100644 index 0000000..091ee99 --- /dev/null +++ b/Qwen3-0.6B-Base.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c728e4fe4abb28cde33b59cd66396e62b2ef755f53db44cdb54e9655b863782 +size 396704960 diff --git a/Qwen3-0.6B-Base.Q4_K_S.gguf b/Qwen3-0.6B-Base.Q4_K_S.gguf new file mode 100644 index 0000000..2358342 --- /dev/null +++ b/Qwen3-0.6B-Base.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ba759e9ce54b7d059d19a64aa6f6365ac07cc522fdd33c34ccec4487f37b798 +size 383270080 diff --git a/Qwen3-0.6B-Base.Q5_K_M.gguf b/Qwen3-0.6B-Base.Q5_K_M.gguf new file mode 100644 index 0000000..376966b --- /dev/null +++ b/Qwen3-0.6B-Base.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f4c79b95ad67509ed69ea88ba1e51b6551c822beacc517094be4dc7108cd207 +size 444415168 diff --git a/Qwen3-0.6B-Base.Q5_K_S.gguf b/Qwen3-0.6B-Base.Q5_K_S.gguf new file mode 100644 index 0000000..8309cf9 --- /dev/null +++ b/Qwen3-0.6B-Base.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ccc7c1827fd5d46fd5c7d6551c4bb4924d05493f1f510bdb09ffc403e97bbd51 +size 436616384 diff --git a/Qwen3-0.6B-Base.Q6_K.gguf b/Qwen3-0.6B-Base.Q6_K.gguf new file mode 100644 index 0000000..0248183 --- /dev/null +++ b/Qwen3-0.6B-Base.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1979947222d24a6a4d6a2c77ea97ddc1257b69e64f940c9d3b59f322d0a47dc +size 495107264 diff --git a/Qwen3-0.6B-Base.Q8_0.gguf b/Qwen3-0.6B-Base.Q8_0.gguf new file mode 100644 index 0000000..7f5f311 --- /dev/null +++ b/Qwen3-0.6B-Base.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b088f1793f6cba9f0c2f77ab835ef6734f205c2159168698c6e1a51b7df168a +size 639447232 diff --git a/Qwen3-0.6B-Base.f16.gguf b/Qwen3-0.6B-Base.f16.gguf new file mode 100644 index 0000000..cff7035 --- /dev/null +++ b/Qwen3-0.6B-Base.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7f3a9d59cc8de30bbc9f1feda8d1e1809b2aadd139b72a0342c769a14002b37 +size 1198182592 diff --git a/README.md b/README.md new file mode 100644 index 0000000..b7c54d4 --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: Qwen/Qwen3-0.6B-Base +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/Qwen/Qwen3-0.6B-Base + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen3-0.6B-Base-i1-GGUF +## 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-Base-GGUF/resolve/main/Qwen3-0.6B-Base.Q2_K.gguf) | Q2_K | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Base-GGUF/resolve/main/Qwen3-0.6B-Base.Q3_K_S.gguf) | Q3_K_S | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Base-GGUF/resolve/main/Qwen3-0.6B-Base.Q3_K_M.gguf) | Q3_K_M | 0.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Base-GGUF/resolve/main/Qwen3-0.6B-Base.Q3_K_L.gguf) | Q3_K_L | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Base-GGUF/resolve/main/Qwen3-0.6B-Base.IQ4_XS.gguf) | IQ4_XS | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Base-GGUF/resolve/main/Qwen3-0.6B-Base.Q4_K_S.gguf) | Q4_K_S | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Base-GGUF/resolve/main/Qwen3-0.6B-Base.Q4_K_M.gguf) | Q4_K_M | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Base-GGUF/resolve/main/Qwen3-0.6B-Base.Q5_K_S.gguf) | Q5_K_S | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Base-GGUF/resolve/main/Qwen3-0.6B-Base.Q5_K_M.gguf) | Q5_K_M | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Base-GGUF/resolve/main/Qwen3-0.6B-Base.Q6_K.gguf) | Q6_K | 0.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Base-GGUF/resolve/main/Qwen3-0.6B-Base.Q8_0.gguf) | Q8_0 | 0.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Base-GGUF/resolve/main/Qwen3-0.6B-Base.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. + +