granite swash 3b a600m
3B total, 598M active · 8k context · Apache 2.0 · released 2026-07-07
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
Experimental base model with no safety alignment, needing transformers > 5.8.0. It runs on Flash Attention 3/4 or eager attention only; SDPA is not supported.
Questions
- What licence is granite swash 3b a600m released under?
- Apache 2.0, which allows commercial use.