--- base_model: zai-org/GLM-4.7 language: - en - zh library_name: transformers license: mit mradermacher: readme_rev: 1 quantized_by: mradermacher --- ## About static quants of https://huggingface.co/zai-org/GLM-4.7 ***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#GLM-4.7-GGUF).*** weighted/imatrix quants are available at https://huggingface.co/mradermacher/GLM-4.7-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/GLM-4.7-GGUF/resolve/main/GLM-4.7.Q2_K.gguf) | Q2_K | 130.7 | | | [GGUF](https://huggingface.co/mradermacher/GLM-4.7-GGUF/resolve/main/GLM-4.7.Q3_K_S.gguf) | Q3_K_S | 154.7 | | | [GGUF](https://huggingface.co/mradermacher/GLM-4.7-GGUF/resolve/main/GLM-4.7.Q3_K_M.gguf) | Q3_K_M | 171.0 | lower quality | | [GGUF](https://huggingface.co/mradermacher/GLM-4.7-GGUF/resolve/main/GLM-4.7.Q3_K_L.gguf) | Q3_K_L | 185.7 | | | [GGUF](https://huggingface.co/mradermacher/GLM-4.7-GGUF/resolve/main/GLM-4.7.IQ4_XS.gguf) | IQ4_XS | 192.7 | | | [P1](https://huggingface.co/mradermacher/GLM-4.7-GGUF/resolve/main/GLM-4.7.Q4_K_S.gguf.part1of5) [P2](https://huggingface.co/mradermacher/GLM-4.7-GGUF/resolve/main/GLM-4.7.Q4_K_S.gguf.part2of5) [P3](https://huggingface.co/mradermacher/GLM-4.7-GGUF/resolve/main/GLM-4.7.Q4_K_S.gguf.part3of5) [P4](https://huggingface.co/mradermacher/GLM-4.7-GGUF/resolve/main/GLM-4.7.Q4_K_S.gguf.part4of5) [P5](https://huggingface.co/mradermacher/GLM-4.7-GGUF/resolve/main/GLM-4.7.Q4_K_S.gguf.part5of5) | Q4_K_S | 203.4 | fast, recommended | | [P1](https://huggingface.co/mradermacher/GLM-4.7-GGUF/resolve/main/GLM-4.7.Q4_K_M.gguf.part1of5) [P2](https://huggingface.co/mradermacher/GLM-4.7-GGUF/resolve/main/GLM-4.7.Q4_K_M.gguf.part2of5) [P3](https://huggingface.co/mradermacher/GLM-4.7-GGUF/resolve/main/GLM-4.7.Q4_K_M.gguf.part3of5) [P4](https://huggingface.co/mradermacher/GLM-4.7-GGUF/resolve/main/GLM-4.7.Q4_K_M.gguf.part4of5) [P5](https://huggingface.co/mradermacher/GLM-4.7-GGUF/resolve/main/GLM-4.7.Q4_K_M.gguf.part5of5) | Q4_K_M | 216.3 | fast, recommended | | [P1](https://huggingface.co/mradermacher/GLM-4.7-GGUF/resolve/main/GLM-4.7.Q5_K_S.gguf.part1of6) [P2](https://huggingface.co/mradermacher/GLM-4.7-GGUF/resolve/main/GLM-4.7.Q5_K_S.gguf.part2of6) [P3](https://huggingface.co/mradermacher/GLM-4.7-GGUF/resolve/main/GLM-4.7.Q5_K_S.gguf.part3of6) [P4](https://huggingface.co/mradermacher/GLM-4.7-GGUF/resolve/main/GLM-4.7.Q5_K_S.gguf.part4of6) [P5](https://huggingface.co/mradermacher/GLM-4.7-GGUF/resolve/main/GLM-4.7.Q5_K_S.gguf.part5of6) [P6](https://huggingface.co/mradermacher/GLM-4.7-GGUF/resolve/main/GLM-4.7.Q5_K_S.gguf.part6of6) | Q5_K_S | 246.8 | | | [P1](https://huggingface.co/mradermacher/GLM-4.7-GGUF/resolve/main/GLM-4.7.Q5_K_M.gguf.part1of6) [P2](https://huggingface.co/mradermacher/GLM-4.7-GGUF/resolve/main/GLM-4.7.Q5_K_M.gguf.part2of6) [P3](https://huggingface.co/mradermacher/GLM-4.7-GGUF/resolve/main/GLM-4.7.Q5_K_M.gguf.part3of6) [P4](https://huggingface.co/mradermacher/GLM-4.7-GGUF/resolve/main/GLM-4.7.Q5_K_M.gguf.part4of6) [P5](https://huggingface.co/mradermacher/GLM-4.7-GGUF/resolve/main/GLM-4.7.Q5_K_M.gguf.part5of6) [P6](https://huggingface.co/mradermacher/GLM-4.7-GGUF/resolve/main/GLM-4.7.Q5_K_M.gguf.part6of6) | Q5_K_M | 254.1 | | | [P1](https://huggingface.co/mradermacher/GLM-4.7-GGUF/resolve/main/GLM-4.7.Q6_K.gguf.part1of7) [P2](https://huggingface.co/mradermacher/GLM-4.7-GGUF/resolve/main/GLM-4.7.Q6_K.gguf.part2of7) [P3](https://huggingface.co/mradermacher/GLM-4.7-GGUF/resolve/main/GLM-4.7.Q6_K.gguf.part3of7) [P4](https://huggingface.co/mradermacher/GLM-4.7-GGUF/resolve/main/GLM-4.7.Q6_K.gguf.part4of7) [P5](https://huggingface.co/mradermacher/GLM-4.7-GGUF/resolve/main/GLM-4.7.Q6_K.gguf.part5of7) [P6](https://huggingface.co/mradermacher/GLM-4.7-GGUF/resolve/main/GLM-4.7.Q6_K.gguf.part6of7) [P7](https://huggingface.co/mradermacher/GLM-4.7-GGUF/resolve/main/GLM-4.7.Q6_K.gguf.part7of7) | Q6_K | 294.3 | very good quality | | [P1](https://huggingface.co/mradermacher/GLM-4.7-GGUF/resolve/main/GLM-4.7.Q8_0.gguf.part1of8) [P2](https://huggingface.co/mradermacher/GLM-4.7-GGUF/resolve/main/GLM-4.7.Q8_0.gguf.part2of8) [P3](https://huggingface.co/mradermacher/GLM-4.7-GGUF/resolve/main/GLM-4.7.Q8_0.gguf.part3of8) [P4](https://huggingface.co/mradermacher/GLM-4.7-GGUF/resolve/main/GLM-4.7.Q8_0.gguf.part4of8) [P5](https://huggingface.co/mradermacher/GLM-4.7-GGUF/resolve/main/GLM-4.7.Q8_0.gguf.part5of8) [P6](https://huggingface.co/mradermacher/GLM-4.7-GGUF/resolve/main/GLM-4.7.Q8_0.gguf.part6of8) [P7](https://huggingface.co/mradermacher/GLM-4.7-GGUF/resolve/main/GLM-4.7.Q8_0.gguf.part7of8) [P8](https://huggingface.co/mradermacher/GLM-4.7-GGUF/resolve/main/GLM-4.7.Q8_0.gguf.part8of8) | Q8_0 | 381.1 | 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.