commit d577d8f32ae67a8bad43fe0fd70cc81ec211b2f2 Author: ModelHub XC Date: Thu May 14 02:48:23 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/gpt-oss-20b-glm-4.6-distill-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d18ef9b --- /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 +gpt-oss-20b-glm-4.6-distill.MXFP4_MOE.gguf filter=lfs diff=lfs merge=lfs -text +gpt-oss-20b-glm-4.6-distill.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +gpt-oss-20b-glm-4.6-distill.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gpt-oss-20b-glm-4.6-distill.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +gpt-oss-20b-glm-4.6-distill.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +gpt-oss-20b-glm-4.6-distill.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gpt-oss-20b-glm-4.6-distill.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +gpt-oss-20b-glm-4.6-distill.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gpt-oss-20b-glm-4.6-distill.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gpt-oss-20b-glm-4.6-distill.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gpt-oss-20b-glm-4.6-distill.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +gpt-oss-20b-glm-4.6-distill.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..ca9ca2d --- /dev/null +++ b/README.md @@ -0,0 +1,78 @@ +--- +base_model: armand0e/gpt-oss-20b-glm-4.6-distill +datasets: +- Liontix/glm-4.6-250x +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- gpt_oss +--- +## About + + + + + + + + + +static quants of https://huggingface.co/armand0e/gpt-oss-20b-glm-4.6-distill + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#gpt-oss-20b-glm-4.6-distill-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/gpt-oss-20b-glm-4.6-distill-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/gpt-oss-20b-glm-4.6-distill-GGUF/resolve/main/gpt-oss-20b-glm-4.6-distill.Q3_K_S.gguf) | Q3_K_S | 12.2 | | +| [GGUF](https://huggingface.co/mradermacher/gpt-oss-20b-glm-4.6-distill-GGUF/resolve/main/gpt-oss-20b-glm-4.6-distill.Q2_K.gguf) | Q2_K | 12.2 | | +| [GGUF](https://huggingface.co/mradermacher/gpt-oss-20b-glm-4.6-distill-GGUF/resolve/main/gpt-oss-20b-glm-4.6-distill.IQ4_XS.gguf) | IQ4_XS | 12.3 | | +| [GGUF](https://huggingface.co/mradermacher/gpt-oss-20b-glm-4.6-distill-GGUF/resolve/main/gpt-oss-20b-glm-4.6-distill.Q3_K_M.gguf) | Q3_K_M | 13.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/gpt-oss-20b-glm-4.6-distill-GGUF/resolve/main/gpt-oss-20b-glm-4.6-distill.Q3_K_L.gguf) | Q3_K_L | 13.4 | | +| [GGUF](https://huggingface.co/mradermacher/gpt-oss-20b-glm-4.6-distill-GGUF/resolve/main/gpt-oss-20b-glm-4.6-distill.Q4_K_S.gguf) | Q4_K_S | 14.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/gpt-oss-20b-glm-4.6-distill-GGUF/resolve/main/gpt-oss-20b-glm-4.6-distill.Q4_K_M.gguf) | Q4_K_M | 15.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/gpt-oss-20b-glm-4.6-distill-GGUF/resolve/main/gpt-oss-20b-glm-4.6-distill.Q5_K_S.gguf) | Q5_K_S | 16.0 | | +| [GGUF](https://huggingface.co/mradermacher/gpt-oss-20b-glm-4.6-distill-GGUF/resolve/main/gpt-oss-20b-glm-4.6-distill.Q5_K_M.gguf) | Q5_K_M | 17.0 | | +| [GGUF](https://huggingface.co/mradermacher/gpt-oss-20b-glm-4.6-distill-GGUF/resolve/main/gpt-oss-20b-glm-4.6-distill.Q6_K.gguf) | Q6_K | 22.3 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/gpt-oss-20b-glm-4.6-distill-GGUF/resolve/main/gpt-oss-20b-glm-4.6-distill.Q8_0.gguf) | Q8_0 | 22.4 | 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/gpt-oss-20b-glm-4.6-distill.IQ4_XS.gguf b/gpt-oss-20b-glm-4.6-distill.IQ4_XS.gguf new file mode 100644 index 0000000..cdd1321 --- /dev/null +++ b/gpt-oss-20b-glm-4.6-distill.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e056c2eb5bd5bb57d0bd31da67dd6542015e7bcf3aa2c71665e19a417bdd8835 +size 12245778560 diff --git a/gpt-oss-20b-glm-4.6-distill.MXFP4_MOE.gguf b/gpt-oss-20b-glm-4.6-distill.MXFP4_MOE.gguf new file mode 100644 index 0000000..94de1d3 --- /dev/null +++ b/gpt-oss-20b-glm-4.6-distill.MXFP4_MOE.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc37e9c16ae23c21480df593c3f9b1bf52a6ed032b634a8620b7d0dc5daf6b26 +size 12109566080 diff --git a/gpt-oss-20b-glm-4.6-distill.Q2_K.gguf b/gpt-oss-20b-glm-4.6-distill.Q2_K.gguf new file mode 100644 index 0000000..5c8cfbd --- /dev/null +++ b/gpt-oss-20b-glm-4.6-distill.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef60740674c148ba8e6beb912f103a74b69054e138d812c837a1b81a0a1cd001 +size 12065513600 diff --git a/gpt-oss-20b-glm-4.6-distill.Q3_K_L.gguf b/gpt-oss-20b-glm-4.6-distill.Q3_K_L.gguf new file mode 100644 index 0000000..0366d4c --- /dev/null +++ b/gpt-oss-20b-glm-4.6-distill.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e3cdcd9218680640c19296a962c2ebb247150e89f75d00179ddde4a1c2aaf5b +size 13335109760 diff --git a/gpt-oss-20b-glm-4.6-distill.Q3_K_M.gguf b/gpt-oss-20b-glm-4.6-distill.Q3_K_M.gguf new file mode 100644 index 0000000..04636a2 --- /dev/null +++ b/gpt-oss-20b-glm-4.6-distill.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ada322c086321a37cf6a5ad93d2bfbedd3d7c1c9bacd47df86bb6a7556b07855 +size 12916150400 diff --git a/gpt-oss-20b-glm-4.6-distill.Q3_K_S.gguf b/gpt-oss-20b-glm-4.6-distill.Q3_K_S.gguf new file mode 100644 index 0000000..084bfbc --- /dev/null +++ b/gpt-oss-20b-glm-4.6-distill.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da380b605c8c68d4e568cbc29a7691e57011a772d238efbe334f604541f891dc +size 12061089920 diff --git a/gpt-oss-20b-glm-4.6-distill.Q4_K_M.gguf b/gpt-oss-20b-glm-4.6-distill.Q4_K_M.gguf new file mode 100644 index 0000000..a8ca438 --- /dev/null +++ b/gpt-oss-20b-glm-4.6-distill.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82ed54de2752b75a50cbd266460811ee7cdc856c1c07e78424635a80cee977c4 +size 15805136000 diff --git a/gpt-oss-20b-glm-4.6-distill.Q4_K_S.gguf b/gpt-oss-20b-glm-4.6-distill.Q4_K_S.gguf new file mode 100644 index 0000000..17e717a --- /dev/null +++ b/gpt-oss-20b-glm-4.6-distill.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e66f8404be11c1a0e1e2e4cd202a2d64efebbd207b7c63e4a9fcb3d411045edb +size 14654241920 diff --git a/gpt-oss-20b-glm-4.6-distill.Q5_K_M.gguf b/gpt-oss-20b-glm-4.6-distill.Q5_K_M.gguf new file mode 100644 index 0000000..657f2f8 --- /dev/null +++ b/gpt-oss-20b-glm-4.6-distill.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18c4ef1efb851e02e45a90002fc07e26a62f163504517164094e894eca703da0 +size 16893061760 diff --git a/gpt-oss-20b-glm-4.6-distill.Q5_K_S.gguf b/gpt-oss-20b-glm-4.6-distill.Q5_K_S.gguf new file mode 100644 index 0000000..a708245 --- /dev/null +++ b/gpt-oss-20b-glm-4.6-distill.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab07ac528412e20b5acd68d5a99c8e23e7f58ff9b6f9b349520cc18c07f63b51 +size 15892204160 diff --git a/gpt-oss-20b-glm-4.6-distill.Q6_K.gguf b/gpt-oss-20b-glm-4.6-distill.Q6_K.gguf new file mode 100644 index 0000000..c19e89c --- /dev/null +++ b/gpt-oss-20b-glm-4.6-distill.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a734827dda265fce08b5e2d1795d9294cab7d7b2a57231a272983a696f66541 +size 22193344640 diff --git a/gpt-oss-20b-glm-4.6-distill.Q8_0.gguf b/gpt-oss-20b-glm-4.6-distill.Q8_0.gguf new file mode 100644 index 0000000..a6a3d45 --- /dev/null +++ b/gpt-oss-20b-glm-4.6-distill.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41d79d0eae12f491ba5e6a8ee22477edbeed3ca4e8820d3d727f75283af5b1a4 +size 22261911680