commit 31cf26c99bdd7e3502ded48fa5fe6c24bac58d84 Author: ModelHub XC Date: Wed Jul 22 23:36:11 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-8B-Esper3-PREVIEW-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..0945e50 --- /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 +Qwen3-8B-Esper3-PREVIEW.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-Esper3-PREVIEW.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-Esper3-PREVIEW.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-Esper3-PREVIEW.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-Esper3-PREVIEW.f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-Esper3-PREVIEW.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-Esper3-PREVIEW.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-Esper3-PREVIEW.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-Esper3-PREVIEW.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-Esper3-PREVIEW.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-Esper3-PREVIEW.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-Esper3-PREVIEW.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-8B-Esper3-PREVIEW.IQ4_XS.gguf b/Qwen3-8B-Esper3-PREVIEW.IQ4_XS.gguf new file mode 100644 index 0000000..300e2ed --- /dev/null +++ b/Qwen3-8B-Esper3-PREVIEW.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0e5fa5a74e72e0c32f24c27a4e1ea483142b2d1c1efeee285ddc46e0f70c964 +size 4593296992 diff --git a/Qwen3-8B-Esper3-PREVIEW.Q2_K.gguf b/Qwen3-8B-Esper3-PREVIEW.Q2_K.gguf new file mode 100644 index 0000000..378d82f --- /dev/null +++ b/Qwen3-8B-Esper3-PREVIEW.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6391f812b8b954919005d10dd748d3256f85d7566dbc24198d9786640777269e +size 3281733216 diff --git a/Qwen3-8B-Esper3-PREVIEW.Q3_K_L.gguf b/Qwen3-8B-Esper3-PREVIEW.Q3_K_L.gguf new file mode 100644 index 0000000..b1cd419 --- /dev/null +++ b/Qwen3-8B-Esper3-PREVIEW.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:133560b9357f1da3d5dbcb2be2b8dc749677be027777542e0707d465c250f4c5 +size 4431394400 diff --git a/Qwen3-8B-Esper3-PREVIEW.Q3_K_M.gguf b/Qwen3-8B-Esper3-PREVIEW.Q3_K_M.gguf new file mode 100644 index 0000000..a00f21c --- /dev/null +++ b/Qwen3-8B-Esper3-PREVIEW.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40d79e2c7e3802eddc872b67fb8d7980f365e714edb8f2ba34358fc63267c98e +size 4124161632 diff --git a/Qwen3-8B-Esper3-PREVIEW.Q3_K_S.gguf b/Qwen3-8B-Esper3-PREVIEW.Q3_K_S.gguf new file mode 100644 index 0000000..8c913fd --- /dev/null +++ b/Qwen3-8B-Esper3-PREVIEW.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6316a580618e83e3638ed09d6ad1e35ebf16046f8abb4052424e7e8fd5c0a47b +size 3769611872 diff --git a/Qwen3-8B-Esper3-PREVIEW.Q4_K_M.gguf b/Qwen3-8B-Esper3-PREVIEW.Q4_K_M.gguf new file mode 100644 index 0000000..6efc023 --- /dev/null +++ b/Qwen3-8B-Esper3-PREVIEW.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5de85abe0e4ee5c3e16551a9bf23b718e6e9cd6da935add16a168fca8cd099d +size 5027784288 diff --git a/Qwen3-8B-Esper3-PREVIEW.Q4_K_S.gguf b/Qwen3-8B-Esper3-PREVIEW.Q4_K_S.gguf new file mode 100644 index 0000000..a801c51 --- /dev/null +++ b/Qwen3-8B-Esper3-PREVIEW.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ed3325204b0ece0b0ccf8cc38dbbebbcbb361e593fb0d3a69381286278daf32 +size 4802012768 diff --git a/Qwen3-8B-Esper3-PREVIEW.Q5_K_M.gguf b/Qwen3-8B-Esper3-PREVIEW.Q5_K_M.gguf new file mode 100644 index 0000000..7bfc7e0 --- /dev/null +++ b/Qwen3-8B-Esper3-PREVIEW.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f6c0f8b282e37e1d52c7fbd840a9c90f9f891bc723ab398c0179976742fc67a +size 5851113056 diff --git a/Qwen3-8B-Esper3-PREVIEW.Q5_K_S.gguf b/Qwen3-8B-Esper3-PREVIEW.Q5_K_S.gguf new file mode 100644 index 0000000..a8d74bc --- /dev/null +++ b/Qwen3-8B-Esper3-PREVIEW.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e56765b60b2690a53d322bff7c2130782f2b96268bfe6799a86ddd8160a0eadf +size 5720761952 diff --git a/Qwen3-8B-Esper3-PREVIEW.Q6_K.gguf b/Qwen3-8B-Esper3-PREVIEW.Q6_K.gguf new file mode 100644 index 0000000..14ee7dd --- /dev/null +++ b/Qwen3-8B-Esper3-PREVIEW.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed39df1e57b0c4e1f10e3fc68c1d6d7cfcfed4f3a140db687928cee9db707a85 +size 6725899872 diff --git a/Qwen3-8B-Esper3-PREVIEW.Q8_0.gguf b/Qwen3-8B-Esper3-PREVIEW.Q8_0.gguf new file mode 100644 index 0000000..edf9bc1 --- /dev/null +++ b/Qwen3-8B-Esper3-PREVIEW.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5fdbb2929d3b0e47a89f4d60f01ecce23b65f458976b6a2db7657a4242274b32 +size 8709518944 diff --git a/Qwen3-8B-Esper3-PREVIEW.f16.gguf b/Qwen3-8B-Esper3-PREVIEW.f16.gguf new file mode 100644 index 0000000..9c0cfb3 --- /dev/null +++ b/Qwen3-8B-Esper3-PREVIEW.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2117c265671ae1b4a878362ec849abd2b2135aef32224eec29885cc2c39b1258 +size 16388044384 diff --git a/README.md b/README.md new file mode 100644 index 0000000..4645190 --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: sequelbox/Qwen3-8B-Esper3-PREVIEW +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/sequelbox/Qwen3-8B-Esper3-PREVIEW + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen3-8B-Esper3-PREVIEW-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/Qwen3-8B-Esper3-PREVIEW-GGUF/resolve/main/Qwen3-8B-Esper3-PREVIEW.Q2_K.gguf) | Q2_K | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-Esper3-PREVIEW-GGUF/resolve/main/Qwen3-8B-Esper3-PREVIEW.Q3_K_S.gguf) | Q3_K_S | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-Esper3-PREVIEW-GGUF/resolve/main/Qwen3-8B-Esper3-PREVIEW.Q3_K_M.gguf) | Q3_K_M | 4.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-Esper3-PREVIEW-GGUF/resolve/main/Qwen3-8B-Esper3-PREVIEW.Q3_K_L.gguf) | Q3_K_L | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-Esper3-PREVIEW-GGUF/resolve/main/Qwen3-8B-Esper3-PREVIEW.IQ4_XS.gguf) | IQ4_XS | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-Esper3-PREVIEW-GGUF/resolve/main/Qwen3-8B-Esper3-PREVIEW.Q4_K_S.gguf) | Q4_K_S | 4.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-Esper3-PREVIEW-GGUF/resolve/main/Qwen3-8B-Esper3-PREVIEW.Q4_K_M.gguf) | Q4_K_M | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-Esper3-PREVIEW-GGUF/resolve/main/Qwen3-8B-Esper3-PREVIEW.Q5_K_S.gguf) | Q5_K_S | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-Esper3-PREVIEW-GGUF/resolve/main/Qwen3-8B-Esper3-PREVIEW.Q5_K_M.gguf) | Q5_K_M | 6.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-Esper3-PREVIEW-GGUF/resolve/main/Qwen3-8B-Esper3-PREVIEW.Q6_K.gguf) | Q6_K | 6.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-Esper3-PREVIEW-GGUF/resolve/main/Qwen3-8B-Esper3-PREVIEW.Q8_0.gguf) | Q8_0 | 8.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-Esper3-PREVIEW-GGUF/resolve/main/Qwen3-8B-Esper3-PREVIEW.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. + +