GLM-4.7-Flash
No written verdict yet. Here is what commenters said.
Why people recommend it
“I used GLM 4.7 flash as my main model for months and it was an incredibly tenacious model and very very fast”
“The 1st local model I found somewhat useful to me was glm-4.7-flash, and it's gotten way better since.”
Show 3 more
“have consistently come back to GLM 4.7 because of its capabilities”
“GLM 4.7 Flash is the main model I use locally for agentic coding work, it's pretty incredible.”
“glm-4.7-flash is a nice local model for this sort of thing”
Caveats and dissent
“GLM 4.7 Flash is a 30b model that was far behind SOTA at launch, and I know that because I pay for z.ai inference and have run the model locally.”
“I had lots of trouble getting GLM-4.7-Flash to work”
Often compared with
Who recommends it in their own words
Threads where it came up
- GLM-4.7-Flash 7 mentions
- Apple announces significant price increases for MacBooks, iPads, more 2 mentions
- Claude Code: connect to a local model when your quota runs out 2 mentions
- Kimi K2.7 Code is generally available in GitHub Copilot 1 mention
- Ask HN: Has anyone replaced Claude/GPT with a local model for daily coding? 1 mention
- Kimi K2.7-Code: open-source coding model with better token efficiency 1 mention
Also written as GLM 4.7 Flash, GLM-4.7 Flash. Data: glm-4-7-flash.json. Quotes are verbatim; the verdict and theme labels are written by a model from these comments, and every clause links to its sources.
All comments 21
“I used GLM 4.7 flash as my main model for months and it was an incredibly tenacious model and very very fast”
“GLM 4.7 Flash is a 30b model that was far behind SOTA at launch, and I know that because I pay for z.ai inference and have run the model locally.”
“From GLM 4.7 flash on 32gb machines with >60tok/s”
“The 1st local model I found somewhat useful to me was glm-4.7-flash, and it's gotten way better since.”
“GLM 4.7 flash was my previous go to for coding but I’ve completely switched to deepseek”
“have consistently come back to GLM 4.7 because of its capabilities”
“GLM 4.7 Flash is the main model I use locally for agentic coding work, it's pretty incredible.”
“Can I use my GLM-4.7-Flash locally?”
“ollama launch opencode --model glm-4.7-flash”
4.7 flash is what I used. In the thinking section it didn't really register the car and washing the car as being necessary, it solely focused on the efficiency of walking vs driving and the distance.
“I had lots of trouble getting GLM-4.7-Flash to work”
“glm-4.7-flash is a nice local model for this sort of thing”
“very few ollamas are new enough for decent modern models like glm-4.7-flash”
“Excited to finally be able to give this a try today.”
“GLM-4.7-Flash seems very promising but is so new.”
“I'm getting usable enough token rates.”
“It's available (with tool parsing, etc.)”
Looks like they have something for 29 USD with 3x the claude code usage: https://z.ai/subscribe
“Seems to work okay, but there usually are subtle bugs in the implementation or chat template”
“https://huggingface.co/inference/models?model=zai-org%2FGLM-4.7-Flash :)”
“Filed under mildly interesting for now.”