commit 23644e500e6b76df04071ff0410a410b92bd9aa2 Author: ModelHub XC Date: Mon Jun 1 03:31:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/RELEX-Qwen3-8B-Base-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..8147c65 --- /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 +RELEX-Qwen3-8B-Base.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +RELEX-Qwen3-8B-Base.f16.gguf filter=lfs diff=lfs merge=lfs -text +RELEX-Qwen3-8B-Base.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +RELEX-Qwen3-8B-Base.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +RELEX-Qwen3-8B-Base.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +RELEX-Qwen3-8B-Base.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +RELEX-Qwen3-8B-Base.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +RELEX-Qwen3-8B-Base.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +RELEX-Qwen3-8B-Base.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +RELEX-Qwen3-8B-Base.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +RELEX-Qwen3-8B-Base.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +RELEX-Qwen3-8B-Base.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..b4a7da8 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: relex-rlvr/RELEX-Qwen3-8B-Base +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/relex-rlvr/RELEX-Qwen3-8B-Base + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#RELEX-Qwen3-8B-Base-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/RELEX-Qwen3-8B-Base-GGUF/resolve/main/RELEX-Qwen3-8B-Base.Q2_K.gguf) | Q2_K | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/RELEX-Qwen3-8B-Base-GGUF/resolve/main/RELEX-Qwen3-8B-Base.Q3_K_S.gguf) | Q3_K_S | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/RELEX-Qwen3-8B-Base-GGUF/resolve/main/RELEX-Qwen3-8B-Base.Q3_K_M.gguf) | Q3_K_M | 4.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/RELEX-Qwen3-8B-Base-GGUF/resolve/main/RELEX-Qwen3-8B-Base.Q3_K_L.gguf) | Q3_K_L | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/RELEX-Qwen3-8B-Base-GGUF/resolve/main/RELEX-Qwen3-8B-Base.IQ4_XS.gguf) | IQ4_XS | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/RELEX-Qwen3-8B-Base-GGUF/resolve/main/RELEX-Qwen3-8B-Base.Q4_K_S.gguf) | Q4_K_S | 4.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/RELEX-Qwen3-8B-Base-GGUF/resolve/main/RELEX-Qwen3-8B-Base.Q4_K_M.gguf) | Q4_K_M | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/RELEX-Qwen3-8B-Base-GGUF/resolve/main/RELEX-Qwen3-8B-Base.Q5_K_S.gguf) | Q5_K_S | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/RELEX-Qwen3-8B-Base-GGUF/resolve/main/RELEX-Qwen3-8B-Base.Q5_K_M.gguf) | Q5_K_M | 6.0 | | +| [GGUF](https://huggingface.co/mradermacher/RELEX-Qwen3-8B-Base-GGUF/resolve/main/RELEX-Qwen3-8B-Base.Q6_K.gguf) | Q6_K | 6.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/RELEX-Qwen3-8B-Base-GGUF/resolve/main/RELEX-Qwen3-8B-Base.Q8_0.gguf) | Q8_0 | 8.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/RELEX-Qwen3-8B-Base-GGUF/resolve/main/RELEX-Qwen3-8B-Base.f16.gguf) | f16 | 16.5 | 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/RELEX-Qwen3-8B-Base.IQ4_XS.gguf b/RELEX-Qwen3-8B-Base.IQ4_XS.gguf new file mode 100644 index 0000000..06718d7 --- /dev/null +++ b/RELEX-Qwen3-8B-Base.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05aa849dbebd6192939b80f00ad0e97f27829e6aaff3f02bb9241e890a206bab +size 4593296640 diff --git a/RELEX-Qwen3-8B-Base.Q2_K.gguf b/RELEX-Qwen3-8B-Base.Q2_K.gguf new file mode 100644 index 0000000..7c574b9 --- /dev/null +++ b/RELEX-Qwen3-8B-Base.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:412d0fca5b5ad9d017de89f03acd30f647e0bfef263915b4ca8f480c500f8846 +size 3281732864 diff --git a/RELEX-Qwen3-8B-Base.Q3_K_L.gguf b/RELEX-Qwen3-8B-Base.Q3_K_L.gguf new file mode 100644 index 0000000..ca74fa9 --- /dev/null +++ b/RELEX-Qwen3-8B-Base.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c569daf4e87c7ec2b28e59515c3ef9b523f01c825f8481b166426bc1ea21efef +size 4431394048 diff --git a/RELEX-Qwen3-8B-Base.Q3_K_M.gguf b/RELEX-Qwen3-8B-Base.Q3_K_M.gguf new file mode 100644 index 0000000..516cfcb --- /dev/null +++ b/RELEX-Qwen3-8B-Base.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48482f1294bdeb3a88809274562867ac248a2b150189f0758e0da3167b5ef7ed +size 4124161280 diff --git a/RELEX-Qwen3-8B-Base.Q3_K_S.gguf b/RELEX-Qwen3-8B-Base.Q3_K_S.gguf new file mode 100644 index 0000000..6cd7bd2 --- /dev/null +++ b/RELEX-Qwen3-8B-Base.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5f0b53c10505caef72fae2fcfd1749d28399281ecdb58495257b1059d82a9fe +size 3769611520 diff --git a/RELEX-Qwen3-8B-Base.Q4_K_M.gguf b/RELEX-Qwen3-8B-Base.Q4_K_M.gguf new file mode 100644 index 0000000..7b69df1 --- /dev/null +++ b/RELEX-Qwen3-8B-Base.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d69ccbc3efa355670b9a977cb1c69abd2e141de5a00e1724602e0eca3b392a6 +size 5027783936 diff --git a/RELEX-Qwen3-8B-Base.Q4_K_S.gguf b/RELEX-Qwen3-8B-Base.Q4_K_S.gguf new file mode 100644 index 0000000..b601f88 --- /dev/null +++ b/RELEX-Qwen3-8B-Base.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0245fc496bba1fa6b4ea6113e2dc95035c13dead32d456ef96ead3c6d96a5af1 +size 4802012416 diff --git a/RELEX-Qwen3-8B-Base.Q5_K_M.gguf b/RELEX-Qwen3-8B-Base.Q5_K_M.gguf new file mode 100644 index 0000000..04d781a --- /dev/null +++ b/RELEX-Qwen3-8B-Base.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25f3bb6077ef5616fc6e9b7460701683d6ce6c5a918e4b213d37feb593d6a0b3 +size 5851112704 diff --git a/RELEX-Qwen3-8B-Base.Q5_K_S.gguf b/RELEX-Qwen3-8B-Base.Q5_K_S.gguf new file mode 100644 index 0000000..2935af2 --- /dev/null +++ b/RELEX-Qwen3-8B-Base.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e09efa39d56c5327f53e9d2fd5c45793365d6a67526f56b9b447e593d69e1653 +size 5720761600 diff --git a/RELEX-Qwen3-8B-Base.Q6_K.gguf b/RELEX-Qwen3-8B-Base.Q6_K.gguf new file mode 100644 index 0000000..166f917 --- /dev/null +++ b/RELEX-Qwen3-8B-Base.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bd56bfb22eb71a74e1734b5cdf151253e4da3dc35b85a2d9284702ef9b6d488 +size 6725899520 diff --git a/RELEX-Qwen3-8B-Base.Q8_0.gguf b/RELEX-Qwen3-8B-Base.Q8_0.gguf new file mode 100644 index 0000000..e97242a --- /dev/null +++ b/RELEX-Qwen3-8B-Base.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43acf4e1e0b6944affea3085127579e3c4b1e2ed5c94a231ec8ef5a69c2e5ee3 +size 8709518592 diff --git a/RELEX-Qwen3-8B-Base.f16.gguf b/RELEX-Qwen3-8B-Base.f16.gguf new file mode 100644 index 0000000..a7dd8bb --- /dev/null +++ b/RELEX-Qwen3-8B-Base.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c0b3e03a027c8d5550bfb5a5855f2d085a89efb28e0921d90cc0938f55bcaab +size 16388044032