# GLM-4.7-Flash 46 Hacker News commenters recommended GLM-4.7-Flash and 11 criticized it, November 2025 to November 2026. It was recommended in 7 of 13 months. It meets the Hacker Approved badge rule. **Verdict:** Recommended as a fast, capable local model for coding and tool calling, roughly on par with mid-size rivals. Critics find it weaker than bigger models and report chat template bugs. ## Why people recommend it - Strong tool calling and agentic coding (4 comments): "GLM 4.7 Flash is the main model I use locally for agentic coding work, it's pretty incredible." ([source](https://news.ycombinator.com/item?id=47680384)) "Community reports highlight strong performance in UI generation and tool calling" ([source](https://news.ycombinator.com/item?id=46686773)) "it actually worked nice in opencode, which I couldn't get Nemotron to do" ([source](https://news.ycombinator.com/item?id=46687108)) - Competes with larger models (4 comments): "it seems to be roughly on par with o3/GPT-5 mini, which would be pretty impressive if it translated to real-world usage" ([source](https://news.ycombinator.com/item?id=46680481)) "it seems to be roughly on par with o3/GPT-5 mini, which is pretty impressive" ([source](https://news.ycombinator.com/item?id=46680451)) "in that space, 4.7 Flash holds its own better than it has any right to." ([source](https://news.ycombinator.com/item?id=46986076)) - Fast on modest hardware (4 comments): "GLM 4.7 flash is also incredibly performant on modest hardware" ([source](https://news.ycombinator.com/item?id=47251900)) "Only model that is competitive in speed is GLM 4.7 flash" ([source](https://news.ycombinator.com/item?id=47250205)) "And you can run quantized versions on old hardware!" ([source](https://news.ycombinator.com/item?id=46986727)) - Good local model choice (4 comments): "glm 4.7 flash which is really good (to be local)" ([source](https://news.ycombinator.com/item?id=47206441)) "glm 4.7-flash that was my local model of choice" ([source](https://news.ycombinator.com/item?id=46874376)) "is a nice local model for this sort of thing" ([source](https://news.ycombinator.com/item?id=46892218)) ## What people warn about - Weaker than bigger models (3 comments): "it is nowhere near as capable as its bigger sibling in use cases beyond typical chat" ([source](https://news.ycombinator.com/item?id=47039128)) "quite fast on the 6000, at around 100 t/s, but definitely not as smart" ([source](https://news.ycombinator.com/item?id=47201850)) "it feels dramatically worse than gpt-oss-20b" ([source](https://news.ycombinator.com/item?id=46684964)) - Chat template and implementation bugs (2 comments): "Seems to work okay, but there usually are subtle bugs in the implementation or chat template" ([source](https://news.ycombinator.com/item?id=46682547)) "It's really fast! But, for now it outputs garbage because there is no (good) template." ([source](https://news.ycombinator.com/item?id=46682994)) - Poor experience, failed tool calls (4 comments): "I had lots of trouble getting GLM-4.7-Flash to work (failed tool calls etc), and even when it works, it's at very low tok/s." ([source](https://news.ycombinator.com/item?id=46892439)) "I recently tried GLM-4.7 Flash 30b and didn’t have a good experience with it at all." ([source](https://news.ycombinator.com/item?id=46833231)) "it seemed to get a bit stuck but I think I probably pushed it too far" ([source](https://news.ycombinator.com/item?id=46691700)) - Slow on some hardware (2 comments): "I had lots of trouble getting GLM-4.7-Flash to work (failed tool calls etc), and even when it works, it's at very low tok/s." ([source](https://news.ycombinator.com/item?id=46892439)) "glm 4.7 flash was not better, but much slower on a 16GB card" ([source](https://news.ycombinator.com/item?id=46990533)) ## Alternatives hackers recommend - [Qwen 3.8 27B](https://hackerapproved.com/p/qwen-3-8-27b.md): 1173 recommend - [Z.ai GLM](https://hackerapproved.com/p/glm-5-2.md): 1043 recommend - [Kimi](https://hackerapproved.com/p/kimi-k3.md): 931 recommend - [Gemma 4](https://hackerapproved.com/p/gemma-4.md): 713 recommend - [Qwen](https://hackerapproved.com/p/qwen.md): 474 recommend ## Cite as Hacker Approved, "GLM-4.7-Flash", https://hackerapproved.com/p/glm-4-7-flash/ (counts from 1,795,640 Hacker News comments, November 2025 to November 2026).