commit eacc1a392c1ba3516e2bf1e2394477f57b3906c0 Author: ModelHub XC Date: Fri Jun 19 05:00:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/nlm-gene-Qwen3-4B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5880278 --- /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 +nlm-gene-Qwen3-4B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +nlm-gene-Qwen3-4B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +nlm-gene-Qwen3-4B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +nlm-gene-Qwen3-4B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +nlm-gene-Qwen3-4B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +nlm-gene-Qwen3-4B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +nlm-gene-Qwen3-4B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +nlm-gene-Qwen3-4B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +nlm-gene-Qwen3-4B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +nlm-gene-Qwen3-4B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +nlm-gene-Qwen3-4B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +nlm-gene-Qwen3-4B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..056f157 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: Dash00/nlm-gene-Qwen3-4B +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Dash00/nlm-gene-Qwen3-4B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#nlm-gene-Qwen3-4B-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/nlm-gene-Qwen3-4B-GGUF/resolve/main/nlm-gene-Qwen3-4B.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/nlm-gene-Qwen3-4B-GGUF/resolve/main/nlm-gene-Qwen3-4B.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/nlm-gene-Qwen3-4B-GGUF/resolve/main/nlm-gene-Qwen3-4B.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/nlm-gene-Qwen3-4B-GGUF/resolve/main/nlm-gene-Qwen3-4B.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/nlm-gene-Qwen3-4B-GGUF/resolve/main/nlm-gene-Qwen3-4B.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/nlm-gene-Qwen3-4B-GGUF/resolve/main/nlm-gene-Qwen3-4B.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/nlm-gene-Qwen3-4B-GGUF/resolve/main/nlm-gene-Qwen3-4B.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/nlm-gene-Qwen3-4B-GGUF/resolve/main/nlm-gene-Qwen3-4B.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/nlm-gene-Qwen3-4B-GGUF/resolve/main/nlm-gene-Qwen3-4B.Q5_K_M.gguf) | Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/nlm-gene-Qwen3-4B-GGUF/resolve/main/nlm-gene-Qwen3-4B.Q6_K.gguf) | Q6_K | 3.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/nlm-gene-Qwen3-4B-GGUF/resolve/main/nlm-gene-Qwen3-4B.Q8_0.gguf) | Q8_0 | 4.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/nlm-gene-Qwen3-4B-GGUF/resolve/main/nlm-gene-Qwen3-4B.f16.gguf) | f16 | 8.1 | 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. + + diff --git a/nlm-gene-Qwen3-4B.IQ4_XS.gguf b/nlm-gene-Qwen3-4B.IQ4_XS.gguf new file mode 100644 index 0000000..ab07174 --- /dev/null +++ b/nlm-gene-Qwen3-4B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2431c5fb8f24a34f2c57ba0f97d41eaaf2fdc8b83ff0b128f0ea2ae297dde7a1 +size 2285749440 diff --git a/nlm-gene-Qwen3-4B.Q2_K.gguf b/nlm-gene-Qwen3-4B.Q2_K.gguf new file mode 100644 index 0000000..69925d6 --- /dev/null +++ b/nlm-gene-Qwen3-4B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e477f33450d878162a92607da9cf1681aca3158c53eab711aadf60c5c7d5f59e +size 1668932800 diff --git a/nlm-gene-Qwen3-4B.Q3_K_L.gguf b/nlm-gene-Qwen3-4B.Q3_K_L.gguf new file mode 100644 index 0000000..7751033 --- /dev/null +++ b/nlm-gene-Qwen3-4B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec44204bbda5fb62c627747782ce7ff17d4abb15a4f43bf5e96e9fd0acb69b95 +size 2239218880 diff --git a/nlm-gene-Qwen3-4B.Q3_K_M.gguf b/nlm-gene-Qwen3-4B.Q3_K_M.gguf new file mode 100644 index 0000000..1272f12 --- /dev/null +++ b/nlm-gene-Qwen3-4B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8304cfcd6cef496ec291296e252135ca3fee5aefd2bc1d461d3c795a7f48cbc2 +size 2075051200 diff --git a/nlm-gene-Qwen3-4B.Q3_K_S.gguf b/nlm-gene-Qwen3-4B.Q3_K_S.gguf new file mode 100644 index 0000000..8f0bc40 --- /dev/null +++ b/nlm-gene-Qwen3-4B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32a34253eda0935686b62a3b8560c393e3ef7837debe31975d77ad61a233db65 +size 1886430400 diff --git a/nlm-gene-Qwen3-4B.Q4_K_M.gguf b/nlm-gene-Qwen3-4B.Q4_K_M.gguf new file mode 100644 index 0000000..f742956 --- /dev/null +++ b/nlm-gene-Qwen3-4B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30185c3fe38a45a5777af71af191a8f270e343e707530aebb144d220ba1e03f1 +size 2496713920 diff --git a/nlm-gene-Qwen3-4B.Q4_K_S.gguf b/nlm-gene-Qwen3-4B.Q4_K_S.gguf new file mode 100644 index 0000000..79751cf --- /dev/null +++ b/nlm-gene-Qwen3-4B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4b5816459c95e71d68173166dfc277374701abb3b0dce5147d4bc98a49fdff6 +size 2382742720 diff --git a/nlm-gene-Qwen3-4B.Q5_K_M.gguf b/nlm-gene-Qwen3-4B.Q5_K_M.gguf new file mode 100644 index 0000000..2e376dd --- /dev/null +++ b/nlm-gene-Qwen3-4B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e2435e1fe025a2af72c51b1be6263ac3c37e68da486b1ce4e7969f993cc2ea0 +size 2888946880 diff --git a/nlm-gene-Qwen3-4B.Q5_K_S.gguf b/nlm-gene-Qwen3-4B.Q5_K_S.gguf new file mode 100644 index 0000000..6521e1d --- /dev/null +++ b/nlm-gene-Qwen3-4B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb76721d72622dfccf6d0952ffc1538c4ea78bb121c61c49a4cd6cee62e0e6d6 +size 2823144640 diff --git a/nlm-gene-Qwen3-4B.Q6_K.gguf b/nlm-gene-Qwen3-4B.Q6_K.gguf new file mode 100644 index 0000000..78bf312 --- /dev/null +++ b/nlm-gene-Qwen3-4B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7363dcc80e6132660a5d27bc5938f9b4083bedb5e1948d6eff5a75cfc7559bc2 +size 3305694400 diff --git a/nlm-gene-Qwen3-4B.Q8_0.gguf b/nlm-gene-Qwen3-4B.Q8_0.gguf new file mode 100644 index 0000000..d2dff2c --- /dev/null +++ b/nlm-gene-Qwen3-4B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99f14a2593da55e93057670f03f8301511465cc96027e1a3ef966de4e382a076 +size 4279672832 diff --git a/nlm-gene-Qwen3-4B.f16.gguf b/nlm-gene-Qwen3-4B.f16.gguf new file mode 100644 index 0000000..be4c669 --- /dev/null +++ b/nlm-gene-Qwen3-4B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56993740fdc809e6b28c2b18565393e8cee3cca0e630d5f6a7098795623335c7 +size 8049912032