commit 76a1acd96098d56453105abefeefa67cc9773281 Author: ModelHub XC Date: Sat May 23 21:19:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Quasar-3.3-Max-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..3f386ef --- /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 +Quasar-3.3-Max.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Quasar-3.3-Max.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Quasar-3.3-Max.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Quasar-3.3-Max.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Quasar-3.3-Max.f16.gguf filter=lfs diff=lfs merge=lfs -text +Quasar-3.3-Max.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Quasar-3.3-Max.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Quasar-3.3-Max.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Quasar-3.3-Max.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Quasar-3.3-Max.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Quasar-3.3-Max.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Quasar-3.3-Max.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Quasar-3.3-Max.IQ4_XS.gguf b/Quasar-3.3-Max.IQ4_XS.gguf new file mode 100644 index 0000000..bfd2f96 --- /dev/null +++ b/Quasar-3.3-Max.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4dedcf5eb17767491a9cdc4f8d128dda5e5c15583ffffe652e4edf1c3e113ee +size 4250299232 diff --git a/Quasar-3.3-Max.Q2_K.gguf b/Quasar-3.3-Max.Q2_K.gguf new file mode 100644 index 0000000..6c92023 --- /dev/null +++ b/Quasar-3.3-Max.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86ac03ed923150c11d830a6e4c3e3ff2d79f802e577e047e261b0afe2056a641 +size 3015940960 diff --git a/Quasar-3.3-Max.Q3_K_L.gguf b/Quasar-3.3-Max.Q3_K_L.gguf new file mode 100644 index 0000000..47d1993 --- /dev/null +++ b/Quasar-3.3-Max.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14bf5b48e66ada527963074c052afe7f715423faaf8fd513504af38182746d56 +size 4088460128 diff --git a/Quasar-3.3-Max.Q3_K_M.gguf b/Quasar-3.3-Max.Q3_K_M.gguf new file mode 100644 index 0000000..cadd7d1 --- /dev/null +++ b/Quasar-3.3-Max.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dbae24f5822eb1e43f4bb1053151f75a11105e9632f6232b6e18a818af99239b +size 3808392032 diff --git a/Quasar-3.3-Max.Q3_K_S.gguf b/Quasar-3.3-Max.Q3_K_S.gguf new file mode 100644 index 0000000..b2a84b3 --- /dev/null +++ b/Quasar-3.3-Max.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8badfa77aeffb4cfbb21b7da28eb1087cd8e030b9c9141c1ab6933418f65d0c3 +size 3492369248 diff --git a/Quasar-3.3-Max.Q4_K_M.gguf b/Quasar-3.3-Max.Q4_K_M.gguf new file mode 100644 index 0000000..9e11d77 --- /dev/null +++ b/Quasar-3.3-Max.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:903b57bf2b56578655a347a9eed618e1ec8c083461b927ade6d6678b89f46984 +size 4683074400 diff --git a/Quasar-3.3-Max.Q4_K_S.gguf b/Quasar-3.3-Max.Q4_K_S.gguf new file mode 100644 index 0000000..f8ce39a --- /dev/null +++ b/Quasar-3.3-Max.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6faf162129ff05df6b89c2959833a8013fd61115ecf67bc109fadca763c154f2 +size 4457769824 diff --git a/Quasar-3.3-Max.Q5_K_M.gguf b/Quasar-3.3-Max.Q5_K_M.gguf new file mode 100644 index 0000000..6392d59 --- /dev/null +++ b/Quasar-3.3-Max.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08fbc28edb78b3da7025f9cb8e05221d8b656e876c5b34fd7db9ad3d5c21b385 +size 5444832096 diff --git a/Quasar-3.3-Max.Q5_K_S.gguf b/Quasar-3.3-Max.Q5_K_S.gguf new file mode 100644 index 0000000..06170eb --- /dev/null +++ b/Quasar-3.3-Max.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:364997ce00f40654138648f6a446d49ac79f8141dc0a8785e46886baea5d8248 +size 5315177312 diff --git a/Quasar-3.3-Max.Q6_K.gguf b/Quasar-3.3-Max.Q6_K.gguf new file mode 100644 index 0000000..6259a82 --- /dev/null +++ b/Quasar-3.3-Max.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0beaa873f54f6503bbd0f12ca9bd54906830aec9255600b0e3233c24a5583a6 +size 6254199648 diff --git a/Quasar-3.3-Max.Q8_0.gguf b/Quasar-3.3-Max.Q8_0.gguf new file mode 100644 index 0000000..49ef69b --- /dev/null +++ b/Quasar-3.3-Max.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da892623a00d30345e9659340b2529176a373cd4a82203a2053b10f65547313d +size 8098526048 diff --git a/Quasar-3.3-Max.f16.gguf b/Quasar-3.3-Max.f16.gguf new file mode 100644 index 0000000..87c4641 --- /dev/null +++ b/Quasar-3.3-Max.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16007d0c60aa47b9bf5950539c00861059681c4c1a72af1c7f0eb21ba576def7 +size 15237854048 diff --git a/README.md b/README.md new file mode 100644 index 0000000..9e3802d --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +base_model: silx-ai/Quasar-3.3-Max +datasets: eyad-silx/Quasar-Max-3.3 +language: +- en +library_name: transformers +model_name: Quasar-3.0-Max +quantized_by: mradermacher +tags: +- rl +- silx +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/silx-ai/Quasar-3.3-Max + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Quasar-3.3-Max-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/Quasar-3.3-Max-GGUF/resolve/main/Quasar-3.3-Max.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/Quasar-3.3-Max-GGUF/resolve/main/Quasar-3.3-Max.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Quasar-3.3-Max-GGUF/resolve/main/Quasar-3.3-Max.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Quasar-3.3-Max-GGUF/resolve/main/Quasar-3.3-Max.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/Quasar-3.3-Max-GGUF/resolve/main/Quasar-3.3-Max.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Quasar-3.3-Max-GGUF/resolve/main/Quasar-3.3-Max.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Quasar-3.3-Max-GGUF/resolve/main/Quasar-3.3-Max.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Quasar-3.3-Max-GGUF/resolve/main/Quasar-3.3-Max.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/Quasar-3.3-Max-GGUF/resolve/main/Quasar-3.3-Max.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Quasar-3.3-Max-GGUF/resolve/main/Quasar-3.3-Max.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Quasar-3.3-Max-GGUF/resolve/main/Quasar-3.3-Max.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Quasar-3.3-Max-GGUF/resolve/main/Quasar-3.3-Max.f16.gguf) | f16 | 15.3 | 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. + +