commit 9cdf9cc497ced850287ea6457a8100f454142e90 Author: ModelHub XC Date: Thu Jun 25 15:45:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/glm-muse-elite-v3-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..8d59d3c --- /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 +glm-muse-elite-v3.f16.gguf filter=lfs diff=lfs merge=lfs -text +glm-muse-elite-v3.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +glm-muse-elite-v3.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +glm-muse-elite-v3.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +glm-muse-elite-v3.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +glm-muse-elite-v3.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +glm-muse-elite-v3.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +glm-muse-elite-v3.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +glm-muse-elite-v3.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +glm-muse-elite-v3.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +glm-muse-elite-v3.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +glm-muse-elite-v3.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..df3cafe --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: MCult01/glm-muse-elite-v3 +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- glm4 +--- +## About + + + + + + + + + +static quants of https://huggingface.co/MCult01/glm-muse-elite-v3 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#glm-muse-elite-v3-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/glm-muse-elite-v3-GGUF/resolve/main/glm-muse-elite-v3.Q2_K.gguf) | Q2_K | 4.1 | | +| [GGUF](https://huggingface.co/mradermacher/glm-muse-elite-v3-GGUF/resolve/main/glm-muse-elite-v3.Q3_K_S.gguf) | Q3_K_S | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/glm-muse-elite-v3-GGUF/resolve/main/glm-muse-elite-v3.Q3_K_M.gguf) | Q3_K_M | 5.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/glm-muse-elite-v3-GGUF/resolve/main/glm-muse-elite-v3.Q3_K_L.gguf) | Q3_K_L | 5.3 | | +| [GGUF](https://huggingface.co/mradermacher/glm-muse-elite-v3-GGUF/resolve/main/glm-muse-elite-v3.IQ4_XS.gguf) | IQ4_XS | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/glm-muse-elite-v3-GGUF/resolve/main/glm-muse-elite-v3.Q4_K_S.gguf) | Q4_K_S | 5.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/glm-muse-elite-v3-GGUF/resolve/main/glm-muse-elite-v3.Q4_K_M.gguf) | Q4_K_M | 6.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/glm-muse-elite-v3-GGUF/resolve/main/glm-muse-elite-v3.Q5_K_S.gguf) | Q5_K_S | 6.8 | | +| [GGUF](https://huggingface.co/mradermacher/glm-muse-elite-v3-GGUF/resolve/main/glm-muse-elite-v3.Q5_K_M.gguf) | Q5_K_M | 7.2 | | +| [GGUF](https://huggingface.co/mradermacher/glm-muse-elite-v3-GGUF/resolve/main/glm-muse-elite-v3.Q6_K.gguf) | Q6_K | 8.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/glm-muse-elite-v3-GGUF/resolve/main/glm-muse-elite-v3.Q8_0.gguf) | Q8_0 | 10.1 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/glm-muse-elite-v3-GGUF/resolve/main/glm-muse-elite-v3.f16.gguf) | f16 | 18.9 | 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/glm-muse-elite-v3.IQ4_XS.gguf b/glm-muse-elite-v3.IQ4_XS.gguf new file mode 100644 index 0000000..1b41c09 --- /dev/null +++ b/glm-muse-elite-v3.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2aefd28de9ed6994b914770f972df6bce430aa17dc23c620b54c0379b5c163a +size 5314869216 diff --git a/glm-muse-elite-v3.Q2_K.gguf b/glm-muse-elite-v3.Q2_K.gguf new file mode 100644 index 0000000..46aa002 --- /dev/null +++ b/glm-muse-elite-v3.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5704fa03d06424544bf87d289b77df4255e7b34e04c653af617e13a802e10181 +size 4006344672 diff --git a/glm-muse-elite-v3.Q3_K_L.gguf b/glm-muse-elite-v3.Q3_K_L.gguf new file mode 100644 index 0000000..b9520f1 --- /dev/null +++ b/glm-muse-elite-v3.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a23615d44f94563124bb15afa46d1575354f96a162ffceefcfefdf708497d31 +size 5196609504 diff --git a/glm-muse-elite-v3.Q3_K_M.gguf b/glm-muse-elite-v3.Q3_K_M.gguf new file mode 100644 index 0000000..86b4181 --- /dev/null +++ b/glm-muse-elite-v3.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95846be12bf4b829c6eab87a6badba24e07075f5300a1333be0e41d26fb3ab34 +size 4974508000 diff --git a/glm-muse-elite-v3.Q3_K_S.gguf b/glm-muse-elite-v3.Q3_K_S.gguf new file mode 100644 index 0000000..4707649 --- /dev/null +++ b/glm-muse-elite-v3.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f6891224f74979e96743a3bafce240316f6ac3dcd4610760f49b4766b7d6ea3 +size 4592039904 diff --git a/glm-muse-elite-v3.Q4_K_M.gguf b/glm-muse-elite-v3.Q4_K_M.gguf new file mode 100644 index 0000000..d33a331 --- /dev/null +++ b/glm-muse-elite-v3.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9130856fed05180f33a83224efe692adb212c6bd9a9f641ddabac428e833805 +size 6166575072 diff --git a/glm-muse-elite-v3.Q4_K_S.gguf b/glm-muse-elite-v3.Q4_K_S.gguf new file mode 100644 index 0000000..e37b42c --- /dev/null +++ b/glm-muse-elite-v3.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49731e24e444f12aac8bb46761c5c97c46439bd2fb88cf4dc447bb93cd993f66 +size 5758482400 diff --git a/glm-muse-elite-v3.Q5_K_M.gguf b/glm-muse-elite-v3.Q5_K_M.gguf new file mode 100644 index 0000000..8ab90a2 --- /dev/null +++ b/glm-muse-elite-v3.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dbb9451dd53c4a67a3be72718981bf4b1f9e9d8567746b3d9eb0dfb75852df54 +size 7050917856 diff --git a/glm-muse-elite-v3.Q5_K_S.gguf b/glm-muse-elite-v3.Q5_K_S.gguf new file mode 100644 index 0000000..0740d26 --- /dev/null +++ b/glm-muse-elite-v3.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1ac895ffdd7faf4f41b9ccf43cb7e668646bd695e7adec05358bf92c0cfd656 +size 6697514976 diff --git a/glm-muse-elite-v3.Q6_K.gguf b/glm-muse-elite-v3.Q6_K.gguf new file mode 100644 index 0000000..3a068cf --- /dev/null +++ b/glm-muse-elite-v3.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f86783ad73f917f107bea146c7d47644eb1270b7c2cf1964266d20b8a503bf58 +size 8266643424 diff --git a/glm-muse-elite-v3.Q8_0.gguf b/glm-muse-elite-v3.Q8_0.gguf new file mode 100644 index 0000000..bdd4cb8 --- /dev/null +++ b/glm-muse-elite-v3.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34d4fd9299b4c88d16fa2c393b7735bd77bfbac96107237c2560891a674f021f +size 9999611872 diff --git a/glm-muse-elite-v3.f16.gguf b/glm-muse-elite-v3.f16.gguf new file mode 100644 index 0000000..d1f8e78 --- /dev/null +++ b/glm-muse-elite-v3.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e01451497200b88941310133b3e0a9f2aa51415e46c6712d3d3bf157d45ce2c +size 18811582432