GLM 4.6
356.8B total, 37.6B active · 198k context · MIT · released 2025-09-29
chatcodingagenticreasoning
What to run it on in the UK
Fully in memory at 64k context, priced at retailers today.
Nothing we price holds this model fully in memory.
All hardware that runs it
Everything we price, best value first. Two cards split the model by layers.
Nothing we price can run it at this context.
Memory needed
Weights, KV cache and runtime buffers at each context length (KV cache at fp16).
| Quant | File |
|---|
Run it
Copy a command for the runtime you use.
No published builds to run yet.
Notes
Uses the same inference method as GLM-4.5; the card recommends temperature 1.0, and top_p 0.95 with top_k 40 for code tasks. Supports tool use during inference, including tool calls inside thinking mode for search agents.
Questions
- What licence is GLM 4.6 released under?
- MIT, which allows commercial use.