commit 0d782c615ce43fe7fff883c796d3a63c4288c79a Author: ModelHub XC Date: Tue Jul 21 01:30:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/LUFFY_Qwen3-4B-Instruct-2507-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f5a9bdc --- /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 +LUFFY_Qwen3-4B-Instruct-2507.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +LUFFY_Qwen3-4B-Instruct-2507.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +LUFFY_Qwen3-4B-Instruct-2507.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +LUFFY_Qwen3-4B-Instruct-2507.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LUFFY_Qwen3-4B-Instruct-2507.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LUFFY_Qwen3-4B-Instruct-2507.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LUFFY_Qwen3-4B-Instruct-2507.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LUFFY_Qwen3-4B-Instruct-2507.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LUFFY_Qwen3-4B-Instruct-2507.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LUFFY_Qwen3-4B-Instruct-2507.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +LUFFY_Qwen3-4B-Instruct-2507.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +LUFFY_Qwen3-4B-Instruct-2507.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/LUFFY_Qwen3-4B-Instruct-2507.IQ4_XS.gguf b/LUFFY_Qwen3-4B-Instruct-2507.IQ4_XS.gguf new file mode 100644 index 0000000..3a07d0d --- /dev/null +++ b/LUFFY_Qwen3-4B-Instruct-2507.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:810928e43f77eb5ae2062ef1d98392a355a2ef6610af55559d87e36efcd318ef +size 2492947904 diff --git a/LUFFY_Qwen3-4B-Instruct-2507.Q2_K.gguf b/LUFFY_Qwen3-4B-Instruct-2507.Q2_K.gguf new file mode 100644 index 0000000..a5929c0 --- /dev/null +++ b/LUFFY_Qwen3-4B-Instruct-2507.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:008be8a7c8a7fe92f46ba0ac2ce25a32249e2a23bc02aafb05005007854a6506 +size 1797124544 diff --git a/LUFFY_Qwen3-4B-Instruct-2507.Q3_K_L.gguf b/LUFFY_Qwen3-4B-Instruct-2507.Q3_K_L.gguf new file mode 100644 index 0000000..f317777 --- /dev/null +++ b/LUFFY_Qwen3-4B-Instruct-2507.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac1a097201ec9bd7ab2f81afbab6bebbb4d56e08713cde5b917ad93543f1929c +size 2406913984 diff --git a/LUFFY_Qwen3-4B-Instruct-2507.Q3_K_M.gguf b/LUFFY_Qwen3-4B-Instruct-2507.Q3_K_M.gguf new file mode 100644 index 0000000..5109d0a --- /dev/null +++ b/LUFFY_Qwen3-4B-Instruct-2507.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3bf318b59c779260fae1c4fd7483b32078ce25727dfacee5cf3b026a9391b27 +size 2242746304 diff --git a/LUFFY_Qwen3-4B-Instruct-2507.Q3_K_S.gguf b/LUFFY_Qwen3-4B-Instruct-2507.Q3_K_S.gguf new file mode 100644 index 0000000..29dc797 --- /dev/null +++ b/LUFFY_Qwen3-4B-Instruct-2507.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:080062d2f5a28b9f9e5608c6dad5ec782c8ff719d4bd0cd6b2813fef2e6a5c73 +size 2054125504 diff --git a/LUFFY_Qwen3-4B-Instruct-2507.Q4_K_M.gguf b/LUFFY_Qwen3-4B-Instruct-2507.Q4_K_M.gguf new file mode 100644 index 0000000..cce64b1 --- /dev/null +++ b/LUFFY_Qwen3-4B-Instruct-2507.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05a89581598f4399a4fab7fc425bcc0e2474c6610c9cf941e6aa3dfc64d522db +size 2716067264 diff --git a/LUFFY_Qwen3-4B-Instruct-2507.Q4_K_S.gguf b/LUFFY_Qwen3-4B-Instruct-2507.Q4_K_S.gguf new file mode 100644 index 0000000..2f1f309 --- /dev/null +++ b/LUFFY_Qwen3-4B-Instruct-2507.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ceeccff98238541b6b2a4f024b7379ca9cebe9863eda9dbec9ac1a023fd88052 +size 2602096064 diff --git a/LUFFY_Qwen3-4B-Instruct-2507.Q5_K_M.gguf b/LUFFY_Qwen3-4B-Instruct-2507.Q5_K_M.gguf new file mode 100644 index 0000000..ebe6edf --- /dev/null +++ b/LUFFY_Qwen3-4B-Instruct-2507.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32f4f73b11b8ebf81db8f3c1ff226bec7f6005a78eb76635800091323ec4a5f4 +size 3156919744 diff --git a/LUFFY_Qwen3-4B-Instruct-2507.Q5_K_S.gguf b/LUFFY_Qwen3-4B-Instruct-2507.Q5_K_S.gguf new file mode 100644 index 0000000..659ed74 --- /dev/null +++ b/LUFFY_Qwen3-4B-Instruct-2507.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08c0d0228361686ee3b40bbdfe85e699c32d5a84988dbd5f99012f309186b075 +size 3091117504 diff --git a/LUFFY_Qwen3-4B-Instruct-2507.Q6_K.gguf b/LUFFY_Qwen3-4B-Instruct-2507.Q6_K.gguf new file mode 100644 index 0000000..a27b7ea --- /dev/null +++ b/LUFFY_Qwen3-4B-Instruct-2507.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01af98db172d6f078c8adddbaf103d9199447b067675f12d9132de8d600431d7 +size 3625325504 diff --git a/LUFFY_Qwen3-4B-Instruct-2507.Q8_0.gguf b/LUFFY_Qwen3-4B-Instruct-2507.Q8_0.gguf new file mode 100644 index 0000000..d045c9d --- /dev/null +++ b/LUFFY_Qwen3-4B-Instruct-2507.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e978a17e23548f7907317d1f8064dc946e2ad7c3ed18151ce6686c4d6863b391 +size 4693669824 diff --git a/LUFFY_Qwen3-4B-Instruct-2507.f16.gguf b/LUFFY_Qwen3-4B-Instruct-2507.f16.gguf new file mode 100644 index 0000000..d87bc23 --- /dev/null +++ b/LUFFY_Qwen3-4B-Instruct-2507.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:edb4a32eca5bd52a7b1bb60d6cc09d6676555e3a7a4d1d598e5a2532173bc15f +size 8829196224 diff --git a/README.md b/README.md new file mode 100644 index 0000000..980bdf5 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: baohao/LUFFY_Qwen3-4B-Instruct-2507 +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/baohao/LUFFY_Qwen3-4B-Instruct-2507 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#LUFFY_Qwen3-4B-Instruct-2507-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/LUFFY_Qwen3-4B-Instruct-2507-GGUF/resolve/main/LUFFY_Qwen3-4B-Instruct-2507.Q2_K.gguf) | Q2_K | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/LUFFY_Qwen3-4B-Instruct-2507-GGUF/resolve/main/LUFFY_Qwen3-4B-Instruct-2507.Q3_K_S.gguf) | Q3_K_S | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/LUFFY_Qwen3-4B-Instruct-2507-GGUF/resolve/main/LUFFY_Qwen3-4B-Instruct-2507.Q3_K_M.gguf) | Q3_K_M | 2.3 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/LUFFY_Qwen3-4B-Instruct-2507-GGUF/resolve/main/LUFFY_Qwen3-4B-Instruct-2507.Q3_K_L.gguf) | Q3_K_L | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/LUFFY_Qwen3-4B-Instruct-2507-GGUF/resolve/main/LUFFY_Qwen3-4B-Instruct-2507.IQ4_XS.gguf) | IQ4_XS | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/LUFFY_Qwen3-4B-Instruct-2507-GGUF/resolve/main/LUFFY_Qwen3-4B-Instruct-2507.Q4_K_S.gguf) | Q4_K_S | 2.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LUFFY_Qwen3-4B-Instruct-2507-GGUF/resolve/main/LUFFY_Qwen3-4B-Instruct-2507.Q4_K_M.gguf) | Q4_K_M | 2.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LUFFY_Qwen3-4B-Instruct-2507-GGUF/resolve/main/LUFFY_Qwen3-4B-Instruct-2507.Q5_K_S.gguf) | Q5_K_S | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/LUFFY_Qwen3-4B-Instruct-2507-GGUF/resolve/main/LUFFY_Qwen3-4B-Instruct-2507.Q5_K_M.gguf) | Q5_K_M | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/LUFFY_Qwen3-4B-Instruct-2507-GGUF/resolve/main/LUFFY_Qwen3-4B-Instruct-2507.Q6_K.gguf) | Q6_K | 3.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/LUFFY_Qwen3-4B-Instruct-2507-GGUF/resolve/main/LUFFY_Qwen3-4B-Instruct-2507.Q8_0.gguf) | Q8_0 | 4.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/LUFFY_Qwen3-4B-Instruct-2507-GGUF/resolve/main/LUFFY_Qwen3-4B-Instruct-2507.f16.gguf) | f16 | 8.9 | 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. + +