commit 7ee02c19afd253924dde6a7b76c5ea94d3ee7602 Author: ModelHub XC Date: Wed Jul 15 08:43:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/QLink-s800-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5d4be39 --- /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 +QLink-s800-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +QLink-s800-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +QLink-s800-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +QLink-s800-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +QLink-s800-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +QLink-s800-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +QLink-s800-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +QLink-s800-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text +QLink-s800-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +QLink-s800-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +QLink-s800-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +QLink-s800-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/QLink-s800-8B.IQ4_XS.gguf b/QLink-s800-8B.IQ4_XS.gguf new file mode 100644 index 0000000..dffd5f5 --- /dev/null +++ b/QLink-s800-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d0f968f0c259135e7dbd0b1f7b99da14f6f59a296916163a7c3bef4cbc6dbb6 +size 4593296704 diff --git a/QLink-s800-8B.Q2_K.gguf b/QLink-s800-8B.Q2_K.gguf new file mode 100644 index 0000000..272822d --- /dev/null +++ b/QLink-s800-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73c65bd8c60c3260451e002023ed47d1d2f0a0ac271eda58e8032b6981b1a682 +size 3281732928 diff --git a/QLink-s800-8B.Q3_K_L.gguf b/QLink-s800-8B.Q3_K_L.gguf new file mode 100644 index 0000000..961bcfd --- /dev/null +++ b/QLink-s800-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31f618b58c4c8544e60cb81cf8fd6bd9837d35c8a7a0d3f0a34462e99712a31f +size 4431394112 diff --git a/QLink-s800-8B.Q3_K_M.gguf b/QLink-s800-8B.Q3_K_M.gguf new file mode 100644 index 0000000..84de25b --- /dev/null +++ b/QLink-s800-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45afbe73635a16aeddfa48ac8eb1a1a9fb2e8c98962b1c0e2f74c04291beb79b +size 4124161344 diff --git a/QLink-s800-8B.Q3_K_S.gguf b/QLink-s800-8B.Q3_K_S.gguf new file mode 100644 index 0000000..bc10c3c --- /dev/null +++ b/QLink-s800-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c56eb6ea8f5f38e4e51bb5b8dfb6136301508c30ebfc5e322cb4bc50148df0a +size 3769611584 diff --git a/QLink-s800-8B.Q4_K_M.gguf b/QLink-s800-8B.Q4_K_M.gguf new file mode 100644 index 0000000..db6dd8f --- /dev/null +++ b/QLink-s800-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bcac90bf04c81e42abeaa17dfbf321840aaa579e0d9670a37595dc0b73a6518a +size 5027784000 diff --git a/QLink-s800-8B.Q4_K_S.gguf b/QLink-s800-8B.Q4_K_S.gguf new file mode 100644 index 0000000..79ec31c --- /dev/null +++ b/QLink-s800-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf0f418aa6fbb895ffb06f7fda04fe9943230676d7c230c735fff2ae0c57fb19 +size 4802012480 diff --git a/QLink-s800-8B.Q5_K_M.gguf b/QLink-s800-8B.Q5_K_M.gguf new file mode 100644 index 0000000..2c7740e --- /dev/null +++ b/QLink-s800-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2c65722cfee1ef6b3fed5d759d66f4c321b070d5313fb6b7f263b5d64e74cf1 +size 5851112768 diff --git a/QLink-s800-8B.Q5_K_S.gguf b/QLink-s800-8B.Q5_K_S.gguf new file mode 100644 index 0000000..f5e2b28 --- /dev/null +++ b/QLink-s800-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82f0446588b41b964ed59784268c38e5e1fbcb708e9ba5e6d13ac6b7d894a94b +size 5720761664 diff --git a/QLink-s800-8B.Q6_K.gguf b/QLink-s800-8B.Q6_K.gguf new file mode 100644 index 0000000..17172e6 --- /dev/null +++ b/QLink-s800-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3273d39a6ed23a1d0caa6971ff6551e21c418f3da1066d7bc169551d5a98f5a1 +size 6725899584 diff --git a/QLink-s800-8B.Q8_0.gguf b/QLink-s800-8B.Q8_0.gguf new file mode 100644 index 0000000..b44ab56 --- /dev/null +++ b/QLink-s800-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83dd47b3aa2aa1174ab204564747aadb8c9b77a5e43f3b52b3dcb4e377a5dd5f +size 8709518656 diff --git a/QLink-s800-8B.f16.gguf b/QLink-s800-8B.f16.gguf new file mode 100644 index 0000000..bc0fd9c --- /dev/null +++ b/QLink-s800-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bae91352bc1bdcd93d7cede2ee241159e279aa37dddbac5f3e14c333cd6c3355 +size 16388044096 diff --git a/README.md b/README.md new file mode 100644 index 0000000..7651271 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: Dash00/QLink-s800-8B +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Dash00/QLink-s800-8B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#QLink-s800-8B-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/QLink-s800-8B-GGUF/resolve/main/QLink-s800-8B.Q2_K.gguf) | Q2_K | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/QLink-s800-8B-GGUF/resolve/main/QLink-s800-8B.Q3_K_S.gguf) | Q3_K_S | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/QLink-s800-8B-GGUF/resolve/main/QLink-s800-8B.Q3_K_M.gguf) | Q3_K_M | 4.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/QLink-s800-8B-GGUF/resolve/main/QLink-s800-8B.Q3_K_L.gguf) | Q3_K_L | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/QLink-s800-8B-GGUF/resolve/main/QLink-s800-8B.IQ4_XS.gguf) | IQ4_XS | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/QLink-s800-8B-GGUF/resolve/main/QLink-s800-8B.Q4_K_S.gguf) | Q4_K_S | 4.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/QLink-s800-8B-GGUF/resolve/main/QLink-s800-8B.Q4_K_M.gguf) | Q4_K_M | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/QLink-s800-8B-GGUF/resolve/main/QLink-s800-8B.Q5_K_S.gguf) | Q5_K_S | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/QLink-s800-8B-GGUF/resolve/main/QLink-s800-8B.Q5_K_M.gguf) | Q5_K_M | 6.0 | | +| [GGUF](https://huggingface.co/mradermacher/QLink-s800-8B-GGUF/resolve/main/QLink-s800-8B.Q6_K.gguf) | Q6_K | 6.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/QLink-s800-8B-GGUF/resolve/main/QLink-s800-8B.Q8_0.gguf) | Q8_0 | 8.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/QLink-s800-8B-GGUF/resolve/main/QLink-s800-8B.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. + +