Update README.md

README.md

@@ -7,52 +7,9 @@ license: mit
 pipeline_tag: text-generation
 ---
 
-# GLM-4.6
+2.33 bpw EXL3 quant of [GLM-4.6](https://huggingface.co/zai-org/GLM-4.6)
 
-<div align="center">
-<img src=https://raw.githubusercontent.com/zai-org/GLM-4.5/refs/heads/main/resources/logo.svg width="15%"/>
-</div>
-<p align="center">
-    👋 Join our <a href="https://discord.gg/QR7SARHRxK" target="_blank">Discord</a> community.
-    <br>
-    📖 Check out the GLM-4.6 <a href="https://z.ai/blog/glm-4.6" target="_blank">technical blog</a>, <a href="https://arxiv.org/abs/2508.06471" target="_blank">technical report(GLM-4.5)</a>, and <a href="https://zhipu-ai.feishu.cn/wiki/Gv3swM0Yci7w7Zke9E0crhU7n7D" target="_blank">Zhipu AI technical documentation</a>.
-    <br>
-    📍 Use GLM-4.6 API services on <a href="https://docs.z.ai/guides/llm/glm-4.6">Z.ai API Platform. </a>
-    <br>
-    👉 One click to <a href="https://chat.z.ai">GLM-4.6</a>.
-</p>
+Base quants [provided by MikeRoz](https://huggingface.co/MikeRoz/GLM-4.6-exl3)
 
-## Model Introduction
+This is just a quick mix of the 2.25 bpw quant with attention, dense layers and shared experts in 4.0 bpw. 
 
-Compared with GLM-4.5, **GLM-4.6**  brings several key improvements:
-
-* **Longer context window:** The context window has been expanded from 128K to 200K tokens, enabling the model to handle more complex agentic tasks.
-* **Superior coding performance:** The model achieves higher scores on code benchmarks and demonstrates better real-world performance in applications such as Claude Code、Cline、Roo Code and Kilo Code, including improvements in generating visually polished front-end pages.
-* **Advanced reasoning:** GLM-4.6 shows a clear improvement in reasoning performance and supports tool use during inference, leading to stronger overall capability.
-* **More capable agents:** GLM-4.6 exhibits stronger performance in tool using and search-based agents, and integrates more effectively within agent frameworks.
-* **Refined writing:** Better aligns with human preferences in style and readability, and performs more naturally in role-playing scenarios.
-
-We evaluated GLM-4.6 across eight public benchmarks covering agents, reasoning, and coding. Results show clear gains over GLM-4.5, with GLM-4.6 also holding competitive advantages over leading domestic and international models such as **DeepSeek-V3.1-Terminus** and **Claude Sonnet 4**.
-
-![bench](https://raw.githubusercontent.com/zai-org/GLM-4.5/refs/heads/main/resources/bench_glm46.png)
-
-## Inference
-
-**Both GLM-4.5 and GLM-4.6 use the same inference method.**
-
-you can check our [github](https://github.com/zai-org/GLM-4.5) for more detail.
-
-## Recommended Evaluation Parameters
-
-For general evaluations, we recommend using a **sampling temperature of 1.0**.
-
-For **code-related evaluation tasks** (such as LCB), it is further recommended to set:
-
-- `top_p = 0.95`
-- `top_k = 40`
-
-
-## Evaluation
-
-- For tool-integrated reasoning, please refer to [this doc](https://github.com/zai-org/GLM-4.5/blob/main/resources/glm_4.6_tir_guide.md).
-- For search benchmark, we design a specific format for searching toolcall in thinking mode to support search agent, please refer to [this](https://github.com/zai-org/GLM-4.5/blob/main/resources/trajectory_search.json). for the detailed template.