GLM Z1 32B 0414
32.6B parameters · 32k context · MIT · released 2025-04-08
reasoningcodingchat
What to run it on in Canada
Fully in memory at 128k 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
Requires transformers>=4.51.3; the card recommends enabling YaRN rope scaling (factor 4.0 over 32768 original positions) for inputs over 8,192 tokens, but never states a maximum context length. Recommended sampling is temperature 0.6, top_p 0.95, with up to 30000 new tokens for thinking.
Questions
- What licence is GLM Z1 32B 0414 released under?
- MIT, which allows commercial use.