commit 463c5d43ffc450ff79f7b46eb0d69d90dcef422d Author: ModelHub XC Date: Fri Jun 12 13:16:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/aquif-3.5-8B-Think-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..66d76bf --- /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 +aquif-3.5-8B-Think.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +aquif-3.5-8B-Think.f16.gguf filter=lfs diff=lfs merge=lfs -text +aquif-3.5-8B-Think.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +aquif-3.5-8B-Think.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +aquif-3.5-8B-Think.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +aquif-3.5-8B-Think.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +aquif-3.5-8B-Think.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +aquif-3.5-8B-Think.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +aquif-3.5-8B-Think.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +aquif-3.5-8B-Think.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +aquif-3.5-8B-Think.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +aquif-3.5-8B-Think.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..cc1d555 --- /dev/null +++ b/README.md @@ -0,0 +1,89 @@ +--- +base_model: aquif-ai/aquif-3.5-8B-Think +language: +- en +- de +- it +- pt +- fr +- hi +- es +- th +- zh +- ja +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- language +- aquif +- text-generation-inference +- math +- coding +- small +- aquif-3.5 +--- +## About + + + + + + + + + +static quants of https://huggingface.co/aquif-ai/aquif-3.5-8B-Think + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#aquif-3.5-8B-Think-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/aquif-3.5-8B-Think-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/aquif-3.5-8B-Think-GGUF/resolve/main/aquif-3.5-8B-Think.Q2_K.gguf) | Q2_K | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/aquif-3.5-8B-Think-GGUF/resolve/main/aquif-3.5-8B-Think.Q3_K_S.gguf) | Q3_K_S | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/aquif-3.5-8B-Think-GGUF/resolve/main/aquif-3.5-8B-Think.Q3_K_M.gguf) | Q3_K_M | 4.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/aquif-3.5-8B-Think-GGUF/resolve/main/aquif-3.5-8B-Think.Q3_K_L.gguf) | Q3_K_L | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/aquif-3.5-8B-Think-GGUF/resolve/main/aquif-3.5-8B-Think.IQ4_XS.gguf) | IQ4_XS | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/aquif-3.5-8B-Think-GGUF/resolve/main/aquif-3.5-8B-Think.Q4_K_S.gguf) | Q4_K_S | 4.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/aquif-3.5-8B-Think-GGUF/resolve/main/aquif-3.5-8B-Think.Q4_K_M.gguf) | Q4_K_M | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/aquif-3.5-8B-Think-GGUF/resolve/main/aquif-3.5-8B-Think.Q5_K_S.gguf) | Q5_K_S | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/aquif-3.5-8B-Think-GGUF/resolve/main/aquif-3.5-8B-Think.Q5_K_M.gguf) | Q5_K_M | 5.9 | | +| [GGUF](https://huggingface.co/mradermacher/aquif-3.5-8B-Think-GGUF/resolve/main/aquif-3.5-8B-Think.Q6_K.gguf) | Q6_K | 6.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/aquif-3.5-8B-Think-GGUF/resolve/main/aquif-3.5-8B-Think.Q8_0.gguf) | Q8_0 | 8.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/aquif-3.5-8B-Think-GGUF/resolve/main/aquif-3.5-8B-Think.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/aquif-3.5-8B-Think.IQ4_XS.gguf b/aquif-3.5-8B-Think.IQ4_XS.gguf new file mode 100644 index 0000000..5c20ec6 --- /dev/null +++ b/aquif-3.5-8B-Think.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20874022f0a429fd3442486f51c4cbc62b878039680ab3f8f9de6ad085f31ac0 +size 4591813312 diff --git a/aquif-3.5-8B-Think.Q2_K.gguf b/aquif-3.5-8B-Think.Q2_K.gguf new file mode 100644 index 0000000..e764b96 --- /dev/null +++ b/aquif-3.5-8B-Think.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7342087908155cac56c01b9fbf31110339f16dc091b754ace8fbc89a2ee79dd +size 3280471680 diff --git a/aquif-3.5-8B-Think.Q3_K_L.gguf b/aquif-3.5-8B-Think.Q3_K_L.gguf new file mode 100644 index 0000000..61e1e78 --- /dev/null +++ b/aquif-3.5-8B-Think.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e44c2015de8277ffea5fd45b901062051bb6d09223c488057e1304aa4e966bf +size 4430021792 diff --git a/aquif-3.5-8B-Think.Q3_K_M.gguf b/aquif-3.5-8B-Think.Q3_K_M.gguf new file mode 100644 index 0000000..229eefb --- /dev/null +++ b/aquif-3.5-8B-Think.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37ed98f4723a79f2ea8a215fd2c81977448d240e6c753cd3fbe391ffe9148b5d +size 4122789024 diff --git a/aquif-3.5-8B-Think.Q3_K_S.gguf b/aquif-3.5-8B-Think.Q3_K_S.gguf new file mode 100644 index 0000000..929b18f --- /dev/null +++ b/aquif-3.5-8B-Think.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dffac2c4302807e64a416a710f812d2cb1269de05978e038e732f4090b406265 +size 3768239264 diff --git a/aquif-3.5-8B-Think.Q4_K_M.gguf b/aquif-3.5-8B-Think.Q4_K_M.gguf new file mode 100644 index 0000000..856e4ca --- /dev/null +++ b/aquif-3.5-8B-Think.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f126bebefda71138f3bb55fbe8258ae7cc6a12205f7366cbf67db9ada6c6eb5 +size 5026266432 diff --git a/aquif-3.5-8B-Think.Q4_K_S.gguf b/aquif-3.5-8B-Think.Q4_K_S.gguf new file mode 100644 index 0000000..c7dc68b --- /dev/null +++ b/aquif-3.5-8B-Think.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b4e46f219ac47622d71b084141d7cf7c99d7009e9975d2fe8274787cdf6b6cc +size 4800494912 diff --git a/aquif-3.5-8B-Think.Q5_K_M.gguf b/aquif-3.5-8B-Think.Q5_K_M.gguf new file mode 100644 index 0000000..7e220c3 --- /dev/null +++ b/aquif-3.5-8B-Think.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a503a90f931ffdf5c6493495b578f6a0874a387b2c83a21eec97af04a1da590 +size 5849458496 diff --git a/aquif-3.5-8B-Think.Q5_K_S.gguf b/aquif-3.5-8B-Think.Q5_K_S.gguf new file mode 100644 index 0000000..25730e3 --- /dev/null +++ b/aquif-3.5-8B-Think.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a684347dcdc0f03c14e250d4ba3716a55494cd65dbbaef53bcefeb916c26a13 +size 5719107392 diff --git a/aquif-3.5-8B-Think.Q6_K.gguf b/aquif-3.5-8B-Think.Q6_K.gguf new file mode 100644 index 0000000..6e6208f --- /dev/null +++ b/aquif-3.5-8B-Think.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f860c7450a203a74f2c2c5417c428034966831724627272a4a4de5a705670131 +size 6724100064 diff --git a/aquif-3.5-8B-Think.Q8_0.gguf b/aquif-3.5-8B-Think.Q8_0.gguf new file mode 100644 index 0000000..6758223 --- /dev/null +++ b/aquif-3.5-8B-Think.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d808d6af880c148c8f3f51b0eb0987be38f9366459a686d51acaa8c9380d37b7 +size 8707189408 diff --git a/aquif-3.5-8B-Think.f16.gguf b/aquif-3.5-8B-Think.f16.gguf new file mode 100644 index 0000000..cf78938 --- /dev/null +++ b/aquif-3.5-8B-Think.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:245b4e9d8e5b2f969d898c4acd607c7cf5c060a2b2b9c1f91b1eeecc0fea6ac3 +size 16383664288