GLM-4.7: Advancing the Coding Capability

Re:GLM-4.7: Advancing the Coding Capability by cmrdporcupine on Monday December 22, 2025 @03:34PM (#46358720)

Devstral Small 24b looks promising as something I want to try fine tuning on DSLs, etc. and then embedding in tooling.

[ Parent | on HN ]

Re:GLM-4.7: Advancing the Coding Capability by hedgehog on Monday December 22, 2025 @06:43PM (#46360630)

I haven't tried it yet, but yes. Qwen3 Next 80B works decently in my testing, and fast. I had mixed results with the new Nemotron, but it and the new Qwen models are both very fast to run.

[ Parent | on HN ]

Re:GLM-4.7: Advancing the Coding Capability by mark_l_watson on Tuesday December 23, 2025 @07:51AM (#46364938)

Same experience: on my old M2 Mac with just 32B of memory both Qwen 3 30B and the new Nemotron models are very useful for coding if I prepare a one-shot prompt with directions and relevant code. I don’t like them for agentic coding tools. I have mentioned this elsewhere: it is deeply satisfying to mix local model use with commercial APIs and services.

[ Parent | on HN ]