commit 89ba2b66c0cb35c7ed513f188207fb4d5f24577e Author: ModelHub XC Date: Sat Oct 10 08:41:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-MOE-4x0.6B-2.4B-reasoning-v1.1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..3d18cc5 --- /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-MOE-4x0.6B-2.4B-reasoning-v1.1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-MOE-4x0.6B-2.4B-reasoning-v1.1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-MOE-4x0.6B-2.4B-reasoning-v1.1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-MOE-4x0.6B-2.4B-reasoning-v1.1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-MOE-4x0.6B-2.4B-reasoning-v1.1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-MOE-4x0.6B-2.4B-reasoning-v1.1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-MOE-4x0.6B-2.4B-reasoning-v1.1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-MOE-4x0.6B-2.4B-reasoning-v1.1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-MOE-4x0.6B-2.4B-reasoning-v1.1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-MOE-4x0.6B-2.4B-reasoning-v1.1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-MOE-4x0.6B-2.4B-reasoning-v1.1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-MOE-4x0.6B-2.4B-reasoning-v1.1.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-MOE-4x0.6B-2.4B-reasoning-v1.1.IQ4_XS.gguf b/Qwen3-MOE-4x0.6B-2.4B-reasoning-v1.1.IQ4_XS.gguf new file mode 100644 index 0000000..898973e --- /dev/null +++ b/Qwen3-MOE-4x0.6B-2.4B-reasoning-v1.1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e2e9e434063ce5654172431b495baf0e29839015c6c80497fd2eed82fa3f8ff +size 795298016 diff --git a/Qwen3-MOE-4x0.6B-2.4B-reasoning-v1.1.Q2_K.gguf b/Qwen3-MOE-4x0.6B-2.4B-reasoning-v1.1.Q2_K.gguf new file mode 100644 index 0000000..b99a873 --- /dev/null +++ b/Qwen3-MOE-4x0.6B-2.4B-reasoning-v1.1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57faf5ae0675722ec7bdb452d8e2b922875d91376dd0a0687923168b08cccf0e +size 583649504 diff --git a/Qwen3-MOE-4x0.6B-2.4B-reasoning-v1.1.Q3_K_L.gguf b/Qwen3-MOE-4x0.6B-2.4B-reasoning-v1.1.Q3_K_L.gguf new file mode 100644 index 0000000..70e536e --- /dev/null +++ b/Qwen3-MOE-4x0.6B-2.4B-reasoning-v1.1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1095ea73d17da2b638bc8e3311900deda79edba42fb9042cf3cf530b343a2a0 +size 777701600 diff --git a/Qwen3-MOE-4x0.6B-2.4B-reasoning-v1.1.Q3_K_M.gguf b/Qwen3-MOE-4x0.6B-2.4B-reasoning-v1.1.Q3_K_M.gguf new file mode 100644 index 0000000..a238b36 --- /dev/null +++ b/Qwen3-MOE-4x0.6B-2.4B-reasoning-v1.1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b437566eb38b1c35722aade57d3928ad7f30c7b0c1b86aba1019ef946333852b +size 724486368 diff --git a/Qwen3-MOE-4x0.6B-2.4B-reasoning-v1.1.Q3_K_S.gguf b/Qwen3-MOE-4x0.6B-2.4B-reasoning-v1.1.Q3_K_S.gguf new file mode 100644 index 0000000..5a49545 --- /dev/null +++ b/Qwen3-MOE-4x0.6B-2.4B-reasoning-v1.1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30111220c1fa7fb4f82255a2298955eb6a61eac71d65e8912d378de25ae67ea9 +size 664160480 diff --git a/Qwen3-MOE-4x0.6B-2.4B-reasoning-v1.1.Q4_K_M.gguf b/Qwen3-MOE-4x0.6B-2.4B-reasoning-v1.1.Q4_K_M.gguf new file mode 100644 index 0000000..4bc7927 --- /dev/null +++ b/Qwen3-MOE-4x0.6B-2.4B-reasoning-v1.1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bfc58c931c6c4e3737816ed4c834d7b085dd9dad6da00cf1942d514b9cad09b8 +size 877136096 diff --git a/Qwen3-MOE-4x0.6B-2.4B-reasoning-v1.1.Q4_K_S.gguf b/Qwen3-MOE-4x0.6B-2.4B-reasoning-v1.1.Q4_K_S.gguf new file mode 100644 index 0000000..09672e0 --- /dev/null +++ b/Qwen3-MOE-4x0.6B-2.4B-reasoning-v1.1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75d5516dd0af788fd1650ba10ff1b2f8d1e776ad1b4cdeac0cc45b3843e8dec9 +size 833177824 diff --git a/Qwen3-MOE-4x0.6B-2.4B-reasoning-v1.1.Q5_K_M.gguf b/Qwen3-MOE-4x0.6B-2.4B-reasoning-v1.1.Q5_K_M.gguf new file mode 100644 index 0000000..f967ddf --- /dev/null +++ b/Qwen3-MOE-4x0.6B-2.4B-reasoning-v1.1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c975ce134a61685c391e638e1ef0a9278d21d5f5080009f02777582378687ba7 +size 1007421664 diff --git a/Qwen3-MOE-4x0.6B-2.4B-reasoning-v1.1.Q5_K_S.gguf b/Qwen3-MOE-4x0.6B-2.4B-reasoning-v1.1.Q5_K_S.gguf new file mode 100644 index 0000000..3d74301 --- /dev/null +++ b/Qwen3-MOE-4x0.6B-2.4B-reasoning-v1.1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0e846177acb5108c4bc1e0260f2dc32d8e106d61251227be6cc03513e1318d7 +size 982075616 diff --git a/Qwen3-MOE-4x0.6B-2.4B-reasoning-v1.1.Q6_K.gguf b/Qwen3-MOE-4x0.6B-2.4B-reasoning-v1.1.Q6_K.gguf new file mode 100644 index 0000000..2596bfb --- /dev/null +++ b/Qwen3-MOE-4x0.6B-2.4B-reasoning-v1.1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6280b1394f9b69b2bcff71a476a472c1f1c9ce9984511d16cc9ad69fdef8f9be +size 1145850080 diff --git a/Qwen3-MOE-4x0.6B-2.4B-reasoning-v1.1.Q8_0.gguf b/Qwen3-MOE-4x0.6B-2.4B-reasoning-v1.1.Q8_0.gguf new file mode 100644 index 0000000..6023884 --- /dev/null +++ b/Qwen3-MOE-4x0.6B-2.4B-reasoning-v1.1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:560d1a4e9043f76f87c83a85d2c47b0df46448b3a84e9800fff2e090d8eb71e7 +size 1482177760 diff --git a/Qwen3-MOE-4x0.6B-2.4B-reasoning-v1.1.f16.gguf b/Qwen3-MOE-4x0.6B-2.4B-reasoning-v1.1.f16.gguf new file mode 100644 index 0000000..06d1a58 --- /dev/null +++ b/Qwen3-MOE-4x0.6B-2.4B-reasoning-v1.1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:caa0587ed1fa1f06e52f512d79fbe596a520b688059c05cd4e66314b065cec95 +size 2784091360 diff --git a/README.md b/README.md new file mode 100644 index 0000000..63eeb5a --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: leeminwaan/Qwen3-MOE-4x0.6B-2.4B-reasoning-v1.1 +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + + + + +static quants of https://huggingface.co/leeminwaan/Qwen3-MOE-4x0.6B-2.4B-reasoning-v1.1 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-MOE-4x0.6B-2.4B-reasoning-v1.1-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-MOE-4x0.6B-2.4B-reasoning-v1.1-GGUF/resolve/main/Qwen3-MOE-4x0.6B-2.4B-reasoning-v1.1.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-MOE-4x0.6B-2.4B-reasoning-v1.1-GGUF/resolve/main/Qwen3-MOE-4x0.6B-2.4B-reasoning-v1.1.Q3_K_S.gguf) | Q3_K_S | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-MOE-4x0.6B-2.4B-reasoning-v1.1-GGUF/resolve/main/Qwen3-MOE-4x0.6B-2.4B-reasoning-v1.1.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-MOE-4x0.6B-2.4B-reasoning-v1.1-GGUF/resolve/main/Qwen3-MOE-4x0.6B-2.4B-reasoning-v1.1.Q3_K_L.gguf) | Q3_K_L | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-MOE-4x0.6B-2.4B-reasoning-v1.1-GGUF/resolve/main/Qwen3-MOE-4x0.6B-2.4B-reasoning-v1.1.IQ4_XS.gguf) | IQ4_XS | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-MOE-4x0.6B-2.4B-reasoning-v1.1-GGUF/resolve/main/Qwen3-MOE-4x0.6B-2.4B-reasoning-v1.1.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-MOE-4x0.6B-2.4B-reasoning-v1.1-GGUF/resolve/main/Qwen3-MOE-4x0.6B-2.4B-reasoning-v1.1.Q4_K_M.gguf) | Q4_K_M | 1.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-MOE-4x0.6B-2.4B-reasoning-v1.1-GGUF/resolve/main/Qwen3-MOE-4x0.6B-2.4B-reasoning-v1.1.Q5_K_S.gguf) | Q5_K_S | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-MOE-4x0.6B-2.4B-reasoning-v1.1-GGUF/resolve/main/Qwen3-MOE-4x0.6B-2.4B-reasoning-v1.1.Q5_K_M.gguf) | Q5_K_M | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-MOE-4x0.6B-2.4B-reasoning-v1.1-GGUF/resolve/main/Qwen3-MOE-4x0.6B-2.4B-reasoning-v1.1.Q6_K.gguf) | Q6_K | 1.2 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-MOE-4x0.6B-2.4B-reasoning-v1.1-GGUF/resolve/main/Qwen3-MOE-4x0.6B-2.4B-reasoning-v1.1.Q8_0.gguf) | Q8_0 | 1.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-MOE-4x0.6B-2.4B-reasoning-v1.1-GGUF/resolve/main/Qwen3-MOE-4x0.6B-2.4B-reasoning-v1.1.f16.gguf) | f16 | 2.9 | 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. + +