commit 3c455dc537df80267e758ad9fe1b364274e3a91d Author: ModelHub XC Date: Mon May 25 20:46:21 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3Novel-0.6B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..21727dc --- /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 +Qwen3Novel-0.6B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3Novel-0.6B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3Novel-0.6B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3Novel-0.6B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3Novel-0.6B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3Novel-0.6B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3Novel-0.6B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3Novel-0.6B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3Novel-0.6B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3Novel-0.6B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3Novel-0.6B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3Novel-0.6B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3Novel-0.6B.IQ4_XS.gguf b/Qwen3Novel-0.6B.IQ4_XS.gguf new file mode 100644 index 0000000..e96b250 --- /dev/null +++ b/Qwen3Novel-0.6B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81e5bec1daf9d69882e4582420eca6043b318270cf8cf716af8deb326ff6b1a2 +size 369278048 diff --git a/Qwen3Novel-0.6B.Q2_K.gguf b/Qwen3Novel-0.6B.Q2_K.gguf new file mode 100644 index 0000000..d9e31af --- /dev/null +++ b/Qwen3Novel-0.6B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd3b4d47f0ec6c90083633c65d4321d6402ae949ea7821ca3b548f88c0eb4048 +size 296238176 diff --git a/Qwen3Novel-0.6B.Q3_K_L.gguf b/Qwen3Novel-0.6B.Q3_K_L.gguf new file mode 100644 index 0000000..c8c7a01 --- /dev/null +++ b/Qwen3Novel-0.6B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:235ae4778cec93d5a5c36109b80b530bf7d6c3e9e3c536ab471eda8077959fa5 +size 368491616 diff --git a/Qwen3Novel-0.6B.Q3_K_M.gguf b/Qwen3Novel-0.6B.Q3_K_M.gguf new file mode 100644 index 0000000..c2fa8ec --- /dev/null +++ b/Qwen3Novel-0.6B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ecad70ab758227427bf96fc20f332a0172b87edf3308a318d5b1dc4467adb3a4 +size 347126880 diff --git a/Qwen3Novel-0.6B.Q3_K_S.gguf b/Qwen3Novel-0.6B.Q3_K_S.gguf new file mode 100644 index 0000000..8c6100b --- /dev/null +++ b/Qwen3Novel-0.6B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:523ac755993179b868907a9317ee3badb1d963930b169add45a6d07bad5eda47 +size 323075168 diff --git a/Qwen3Novel-0.6B.Q4_K_M.gguf b/Qwen3Novel-0.6B.Q4_K_M.gguf new file mode 100644 index 0000000..15b72aa --- /dev/null +++ b/Qwen3Novel-0.6B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d486728b3e9812f9b1c39a2194fd047dcb0332788a2305aca66689107897431 +size 396704864 diff --git a/Qwen3Novel-0.6B.Q4_K_S.gguf b/Qwen3Novel-0.6B.Q4_K_S.gguf new file mode 100644 index 0000000..cc2471c --- /dev/null +++ b/Qwen3Novel-0.6B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7c284a3f9c87b97125c5dc0fd67c88ee8b01d572aab0cfa4a1fdeb72b274b3e +size 383269984 diff --git a/Qwen3Novel-0.6B.Q5_K_M.gguf b/Qwen3Novel-0.6B.Q5_K_M.gguf new file mode 100644 index 0000000..bbaf2d0 --- /dev/null +++ b/Qwen3Novel-0.6B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:356c1f9cd5d95ff9e01bef61f91199247ae2b6549a84d30c7d1b83d67a6087c8 +size 444415072 diff --git a/Qwen3Novel-0.6B.Q5_K_S.gguf b/Qwen3Novel-0.6B.Q5_K_S.gguf new file mode 100644 index 0000000..e6cda26 --- /dev/null +++ b/Qwen3Novel-0.6B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fcb61aa1abe8e8be722df4c16f0cd883c4447dc61f66b49b48a6f31c0b172495 +size 436616288 diff --git a/Qwen3Novel-0.6B.Q6_K.gguf b/Qwen3Novel-0.6B.Q6_K.gguf new file mode 100644 index 0000000..50a9cf9 --- /dev/null +++ b/Qwen3Novel-0.6B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1675fe0219f7ed01b057d794008d9b1941129c6461b16dd0e8b43adf725ac8c4 +size 495107168 diff --git a/Qwen3Novel-0.6B.Q8_0.gguf b/Qwen3Novel-0.6B.Q8_0.gguf new file mode 100644 index 0000000..cffc588 --- /dev/null +++ b/Qwen3Novel-0.6B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66a021e725a0744f72075b99f0c81f3ae304eafe361a2a1a276f3e0a4654a4e7 +size 639447136 diff --git a/Qwen3Novel-0.6B.f16.gguf b/Qwen3Novel-0.6B.f16.gguf new file mode 100644 index 0000000..0d5a9e6 --- /dev/null +++ b/Qwen3Novel-0.6B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9643133b3c2d31c0c13982c0e64dfbf9448fafcb6368497533f02c0f8623154 +size 1198182496 diff --git a/README.md b/README.md new file mode 100644 index 0000000..1e2b519 --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: XuezhaOrg/Qwen3Novel-0.6B +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/XuezhaOrg/Qwen3Novel-0.6B + + +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/Qwen3Novel-0.6B-GGUF/resolve/main/Qwen3Novel-0.6B.Q2_K.gguf) | Q2_K | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3Novel-0.6B-GGUF/resolve/main/Qwen3Novel-0.6B.Q3_K_S.gguf) | Q3_K_S | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3Novel-0.6B-GGUF/resolve/main/Qwen3Novel-0.6B.Q3_K_M.gguf) | Q3_K_M | 0.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3Novel-0.6B-GGUF/resolve/main/Qwen3Novel-0.6B.Q3_K_L.gguf) | Q3_K_L | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3Novel-0.6B-GGUF/resolve/main/Qwen3Novel-0.6B.IQ4_XS.gguf) | IQ4_XS | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3Novel-0.6B-GGUF/resolve/main/Qwen3Novel-0.6B.Q4_K_S.gguf) | Q4_K_S | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3Novel-0.6B-GGUF/resolve/main/Qwen3Novel-0.6B.Q4_K_M.gguf) | Q4_K_M | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3Novel-0.6B-GGUF/resolve/main/Qwen3Novel-0.6B.Q5_K_S.gguf) | Q5_K_S | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3Novel-0.6B-GGUF/resolve/main/Qwen3Novel-0.6B.Q5_K_M.gguf) | Q5_K_M | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3Novel-0.6B-GGUF/resolve/main/Qwen3Novel-0.6B.Q6_K.gguf) | Q6_K | 0.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3Novel-0.6B-GGUF/resolve/main/Qwen3Novel-0.6B.Q8_0.gguf) | Q8_0 | 0.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3Novel-0.6B-GGUF/resolve/main/Qwen3Novel-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. + +