commit ca2c9f525a66a5425b8d34f7988fd043df4f8a07 Author: ModelHub XC Date: Wed May 6 09:18:41 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/remnant-glm4-32b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..9fc6cb3 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,46 @@ +*.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 +remnant-glm4-32b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +remnant-glm4-32b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +remnant-glm4-32b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +remnant-glm4-32b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +remnant-glm4-32b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +remnant-glm4-32b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +remnant-glm4-32b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +remnant-glm4-32b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +remnant-glm4-32b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +remnant-glm4-32b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +remnant-glm4-32b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..1a955f2 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: allura-org/remnant-glm4-32b +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +no_imatrix: '[1]4.7397,[2]3.8701,[3]3.6208,nan detected in blk.1.ffn_up.weight' +quantized_by: mradermacher +tags: +- roleplay +- conversational +- axolotl +--- +## About + + + + + + +static quants of https://huggingface.co/allura-org/remnant-glm4-32b + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#remnant-glm4-32b-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/remnant-glm4-32b-GGUF/resolve/main/remnant-glm4-32b.Q2_K.gguf) | Q2_K | 12.4 | | +| [GGUF](https://huggingface.co/mradermacher/remnant-glm4-32b-GGUF/resolve/main/remnant-glm4-32b.Q3_K_S.gguf) | Q3_K_S | 14.5 | | +| [GGUF](https://huggingface.co/mradermacher/remnant-glm4-32b-GGUF/resolve/main/remnant-glm4-32b.Q3_K_M.gguf) | Q3_K_M | 16.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/remnant-glm4-32b-GGUF/resolve/main/remnant-glm4-32b.Q3_K_L.gguf) | Q3_K_L | 17.3 | | +| [GGUF](https://huggingface.co/mradermacher/remnant-glm4-32b-GGUF/resolve/main/remnant-glm4-32b.IQ4_XS.gguf) | IQ4_XS | 17.9 | | +| [GGUF](https://huggingface.co/mradermacher/remnant-glm4-32b-GGUF/resolve/main/remnant-glm4-32b.Q4_K_S.gguf) | Q4_K_S | 18.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/remnant-glm4-32b-GGUF/resolve/main/remnant-glm4-32b.Q4_K_M.gguf) | Q4_K_M | 19.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/remnant-glm4-32b-GGUF/resolve/main/remnant-glm4-32b.Q5_K_S.gguf) | Q5_K_S | 22.6 | | +| [GGUF](https://huggingface.co/mradermacher/remnant-glm4-32b-GGUF/resolve/main/remnant-glm4-32b.Q5_K_M.gguf) | Q5_K_M | 23.2 | | +| [GGUF](https://huggingface.co/mradermacher/remnant-glm4-32b-GGUF/resolve/main/remnant-glm4-32b.Q6_K.gguf) | Q6_K | 26.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/remnant-glm4-32b-GGUF/resolve/main/remnant-glm4-32b.Q8_0.gguf) | Q8_0 | 34.7 | fast, best quality | + +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/remnant-glm4-32b.IQ4_XS.gguf b/remnant-glm4-32b.IQ4_XS.gguf new file mode 100644 index 0000000..58251d7 --- /dev/null +++ b/remnant-glm4-32b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52a4dc85da1273f8ca52cbc7bacef7a4cd4b69561d788a2823a582e5b37baaae +size 17754272032 diff --git a/remnant-glm4-32b.Q2_K.gguf b/remnant-glm4-32b.Q2_K.gguf new file mode 100644 index 0000000..0a2eb3a --- /dev/null +++ b/remnant-glm4-32b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a54dc1e7ec146e8b5cbc0f8795f97245074c388830a2f4a5cead3b40dc8dc17a +size 12292256032 diff --git a/remnant-glm4-32b.Q3_K_L.gguf b/remnant-glm4-32b.Q3_K_L.gguf new file mode 100644 index 0000000..63fd123 --- /dev/null +++ b/remnant-glm4-32b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0af2b4a62a9fb2f7de6a5e003eccf211a854a9a9d414204d561f820219228ce0 +size 17216291104 diff --git a/remnant-glm4-32b.Q3_K_M.gguf b/remnant-glm4-32b.Q3_K_M.gguf new file mode 100644 index 0000000..f2cb80a --- /dev/null +++ b/remnant-glm4-32b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:545577b6628136020d7ac71ae4b40026b37428220de3af371adf3032e030869f +size 15890563360 diff --git a/remnant-glm4-32b.Q3_K_S.gguf b/remnant-glm4-32b.Q3_K_S.gguf new file mode 100644 index 0000000..c653acb --- /dev/null +++ b/remnant-glm4-32b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3f370bedc8764c689e34a9b62448c6bf2d24fb8e03db79cf76cf98f527eb0b9 +size 14371680544 diff --git a/remnant-glm4-32b.Q4_K_M.gguf b/remnant-glm4-32b.Q4_K_M.gguf new file mode 100644 index 0000000..f70051b --- /dev/null +++ b/remnant-glm4-32b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d6a63105e868f3a3e1d1ac9238257e7584d9ab17d97a0ec9fd0b9029e0f232c +size 19680022816 diff --git a/remnant-glm4-32b.Q4_K_S.gguf b/remnant-glm4-32b.Q4_K_S.gguf new file mode 100644 index 0000000..e067e22 --- /dev/null +++ b/remnant-glm4-32b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdd61c439923d5896879603a5f622566ef08a88151cbbb749eefec5433ec371b +size 18697646368 diff --git a/remnant-glm4-32b.Q5_K_M.gguf b/remnant-glm4-32b.Q5_K_M.gguf new file mode 100644 index 0000000..0e9ef2e --- /dev/null +++ b/remnant-glm4-32b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0b014966f67b350e77d6fece8d27b46a7aa36efbe63dfccabc8c212eec0f724 +size 23097463072 diff --git a/remnant-glm4-32b.Q5_K_S.gguf b/remnant-glm4-32b.Q5_K_S.gguf new file mode 100644 index 0000000..2ede935 --- /dev/null +++ b/remnant-glm4-32b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:580bc09f96af9365fde3bb0d9d590a499be6616a0f89073e04f270305d3b38fb +size 22527176992 diff --git a/remnant-glm4-32b.Q6_K.gguf b/remnant-glm4-32b.Q6_K.gguf new file mode 100644 index 0000000..62a0c28 --- /dev/null +++ b/remnant-glm4-32b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:244f2c9714ea7ef61f9641c15ddabeaffcb3efabc5e9e3b1e924c58cd30f76d0 +size 26728493344 diff --git a/remnant-glm4-32b.Q8_0.gguf b/remnant-glm4-32b.Q8_0.gguf new file mode 100644 index 0000000..e73decc --- /dev/null +++ b/remnant-glm4-32b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8220004ca621dedc552f86d4648d858fe9b32700c1c89c39f641fbda4f3df2ad +size 34615226656