commit 2ef94dfea516d5d318163ca66c955084eaa7baa5 Author: ModelHub XC Date: Fri May 1 00:12:07 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-MOE-4x0.6B-2.4B-Writing-Thunder-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c99d3c0 --- /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-Writing-Thunder.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-MOE-4x0.6B-2.4B-Writing-Thunder.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-MOE-4x0.6B-2.4B-Writing-Thunder.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-MOE-4x0.6B-2.4B-Writing-Thunder.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-MOE-4x0.6B-2.4B-Writing-Thunder.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-MOE-4x0.6B-2.4B-Writing-Thunder.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-MOE-4x0.6B-2.4B-Writing-Thunder.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-MOE-4x0.6B-2.4B-Writing-Thunder.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-MOE-4x0.6B-2.4B-Writing-Thunder.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-MOE-4x0.6B-2.4B-Writing-Thunder.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-MOE-4x0.6B-2.4B-Writing-Thunder.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-MOE-4x0.6B-2.4B-Writing-Thunder.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-MOE-4x0.6B-2.4B-Writing-Thunder.IQ4_XS.gguf b/Qwen3-MOE-4x0.6B-2.4B-Writing-Thunder.IQ4_XS.gguf new file mode 100644 index 0000000..138c609 --- /dev/null +++ b/Qwen3-MOE-4x0.6B-2.4B-Writing-Thunder.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2b9b8c0296479906d86ac30a6d02241ab3cad9996bfbbfcc1ac2203ae70c20b +size 877952832 diff --git a/Qwen3-MOE-4x0.6B-2.4B-Writing-Thunder.Q2_K.gguf b/Qwen3-MOE-4x0.6B-2.4B-Writing-Thunder.Q2_K.gguf new file mode 100644 index 0000000..a369aa4 --- /dev/null +++ b/Qwen3-MOE-4x0.6B-2.4B-Writing-Thunder.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:556b21260158203f7c2f1a530592af183b00496c4d43b53ec34444714dd71af6 +size 634701632 diff --git a/Qwen3-MOE-4x0.6B-2.4B-Writing-Thunder.Q3_K_L.gguf b/Qwen3-MOE-4x0.6B-2.4B-Writing-Thunder.Q3_K_L.gguf new file mode 100644 index 0000000..d34086d --- /dev/null +++ b/Qwen3-MOE-4x0.6B-2.4B-Writing-Thunder.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78342dc54b16f2ecb042abc536e02ccf21a62783f9da57ad192d1925858640c5 +size 844555072 diff --git a/Qwen3-MOE-4x0.6B-2.4B-Writing-Thunder.Q3_K_M.gguf b/Qwen3-MOE-4x0.6B-2.4B-Writing-Thunder.Q3_K_M.gguf new file mode 100644 index 0000000..da216d1 --- /dev/null +++ b/Qwen3-MOE-4x0.6B-2.4B-Writing-Thunder.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f602c398d705fe7764cdf56bb5225c28eb5fba45356e55a77f382295ed74460 +size 791339840 diff --git a/Qwen3-MOE-4x0.6B-2.4B-Writing-Thunder.Q3_K_S.gguf b/Qwen3-MOE-4x0.6B-2.4B-Writing-Thunder.Q3_K_S.gguf new file mode 100644 index 0000000..044e782 --- /dev/null +++ b/Qwen3-MOE-4x0.6B-2.4B-Writing-Thunder.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a242c28a0573aa7c3b30b61210ffed9b00dc961c81811c88bd6a5033709a1f9a +size 731013952 diff --git a/Qwen3-MOE-4x0.6B-2.4B-Writing-Thunder.Q4_K_M.gguf b/Qwen3-MOE-4x0.6B-2.4B-Writing-Thunder.Q4_K_M.gguf new file mode 100644 index 0000000..89f8b9e --- /dev/null +++ b/Qwen3-MOE-4x0.6B-2.4B-Writing-Thunder.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91148406848e4d4c5a8845d44a94a6c349cc32efbf80440d7935124235ca10c0 +size 964652864 diff --git a/Qwen3-MOE-4x0.6B-2.4B-Writing-Thunder.Q4_K_S.gguf b/Qwen3-MOE-4x0.6B-2.4B-Writing-Thunder.Q4_K_S.gguf new file mode 100644 index 0000000..5bc6b6b --- /dev/null +++ b/Qwen3-MOE-4x0.6B-2.4B-Writing-Thunder.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9229e3918532c77a4560f67c5787fb68e078e7fa6be73804451adf344e2cad53 +size 920694592 diff --git a/Qwen3-MOE-4x0.6B-2.4B-Writing-Thunder.Q5_K_M.gguf b/Qwen3-MOE-4x0.6B-2.4B-Writing-Thunder.Q5_K_M.gguf new file mode 100644 index 0000000..04734c8 --- /dev/null +++ b/Qwen3-MOE-4x0.6B-2.4B-Writing-Thunder.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:995dd58d861ce26b75fbe4b3ae54f3ad3c4c87e2b720f7c9783a4816d01a6017 +size 1114386240 diff --git a/Qwen3-MOE-4x0.6B-2.4B-Writing-Thunder.Q5_K_S.gguf b/Qwen3-MOE-4x0.6B-2.4B-Writing-Thunder.Q5_K_S.gguf new file mode 100644 index 0000000..bcbdb0a --- /dev/null +++ b/Qwen3-MOE-4x0.6B-2.4B-Writing-Thunder.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62d6a96d44f9b638772a1a7bb867c820077b224aee8cce857c03bcfa04abac1a +size 1089040192 diff --git a/Qwen3-MOE-4x0.6B-2.4B-Writing-Thunder.Q6_K.gguf b/Qwen3-MOE-4x0.6B-2.4B-Writing-Thunder.Q6_K.gguf new file mode 100644 index 0000000..3219a92 --- /dev/null +++ b/Qwen3-MOE-4x0.6B-2.4B-Writing-Thunder.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee86583c64e8d0ac971b1eb3c948677b649034e2c92630b9d84b918a68cae3bc +size 1273477952 diff --git a/Qwen3-MOE-4x0.6B-2.4B-Writing-Thunder.Q8_0.gguf b/Qwen3-MOE-4x0.6B-2.4B-Writing-Thunder.Q8_0.gguf new file mode 100644 index 0000000..b9b9008 --- /dev/null +++ b/Qwen3-MOE-4x0.6B-2.4B-Writing-Thunder.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f28a86f0e7853ade2ce17661301a5e8a0b5589c5c6d2533bbccd791f2aedde38 +size 1647485760 diff --git a/Qwen3-MOE-4x0.6B-2.4B-Writing-Thunder.f16.gguf b/Qwen3-MOE-4x0.6B-2.4B-Writing-Thunder.f16.gguf new file mode 100644 index 0000000..b37f6af --- /dev/null +++ b/Qwen3-MOE-4x0.6B-2.4B-Writing-Thunder.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71936d227c79937465a78c0b2f4c0b464d8261231874f8e7ef70edbf04c41c6b +size 3095257920 diff --git a/README.md b/README.md new file mode 100644 index 0000000..d213c58 --- /dev/null +++ b/README.md @@ -0,0 +1,106 @@ +--- +base_model: DavidAU/Qwen3-MOE-4x0.6B-2.4B-Writing-Thunder +language: +- en +- fr +- zh +- de +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- programming +- code generation +- code +- codeqwen +- programming +- code generation +- code +- codeqwen +- moe +- coding +- coder +- qwen2 +- chat +- qwen +- qwen-coder +- chat +- qwen +- qwen-coder +- moe +- mixture of experts +- 4 experts +- 2 active experts +- 40k context +- qwen3 +- finetune +- qwen3_moe +- creative +- all use cases +- roleplay +- merge +--- +## About + + + + + + + + + +static quants of https://huggingface.co/DavidAU/Qwen3-MOE-4x0.6B-2.4B-Writing-Thunder + + + +***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-Writing-Thunder-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen3-MOE-4x0.6B-2.4B-Writing-Thunder-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-MOE-4x0.6B-2.4B-Writing-Thunder-GGUF/resolve/main/Qwen3-MOE-4x0.6B-2.4B-Writing-Thunder.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-MOE-4x0.6B-2.4B-Writing-Thunder-GGUF/resolve/main/Qwen3-MOE-4x0.6B-2.4B-Writing-Thunder.Q3_K_S.gguf) | Q3_K_S | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-MOE-4x0.6B-2.4B-Writing-Thunder-GGUF/resolve/main/Qwen3-MOE-4x0.6B-2.4B-Writing-Thunder.Q3_K_M.gguf) | Q3_K_M | 0.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-MOE-4x0.6B-2.4B-Writing-Thunder-GGUF/resolve/main/Qwen3-MOE-4x0.6B-2.4B-Writing-Thunder.Q3_K_L.gguf) | Q3_K_L | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-MOE-4x0.6B-2.4B-Writing-Thunder-GGUF/resolve/main/Qwen3-MOE-4x0.6B-2.4B-Writing-Thunder.IQ4_XS.gguf) | IQ4_XS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-MOE-4x0.6B-2.4B-Writing-Thunder-GGUF/resolve/main/Qwen3-MOE-4x0.6B-2.4B-Writing-Thunder.Q4_K_S.gguf) | Q4_K_S | 1.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-MOE-4x0.6B-2.4B-Writing-Thunder-GGUF/resolve/main/Qwen3-MOE-4x0.6B-2.4B-Writing-Thunder.Q4_K_M.gguf) | Q4_K_M | 1.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-MOE-4x0.6B-2.4B-Writing-Thunder-GGUF/resolve/main/Qwen3-MOE-4x0.6B-2.4B-Writing-Thunder.Q5_K_S.gguf) | Q5_K_S | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-MOE-4x0.6B-2.4B-Writing-Thunder-GGUF/resolve/main/Qwen3-MOE-4x0.6B-2.4B-Writing-Thunder.Q5_K_M.gguf) | Q5_K_M | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-MOE-4x0.6B-2.4B-Writing-Thunder-GGUF/resolve/main/Qwen3-MOE-4x0.6B-2.4B-Writing-Thunder.Q6_K.gguf) | Q6_K | 1.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-MOE-4x0.6B-2.4B-Writing-Thunder-GGUF/resolve/main/Qwen3-MOE-4x0.6B-2.4B-Writing-Thunder.Q8_0.gguf) | Q8_0 | 1.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-MOE-4x0.6B-2.4B-Writing-Thunder-GGUF/resolve/main/Qwen3-MOE-4x0.6B-2.4B-Writing-Thunder.f16.gguf) | f16 | 3.2 | 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. + +