Chain Of Thought · tier-2Function Calling · tier-2Multilingual · tier-2Parallel Tool Calls · tier-2Think Budget Control · tier-2
What it fits on
Ordered by predicted speed. Bandwidth sets decode rate; memory decides whether it runs at all.
Every figure here is computed, not measured. Fit is weights at each quantisation against device memory, with a 25% allowance for the KV cache, activations and the OS. Decode rate is the memory-bandwidth roofline at 70% efficiency. Nobody has run this model on these devices. This is a mixture-of-experts model and no card carries active-parameter counts, so these predictions use total parameters and understate the real speed.
Device
Memory
Bandwidth
Best quality
Weights
tok/s
Fastest
Apple M3 Ultra
512.0 GB
819.0 GB/s
q4
335.51 GB
~1.7
~1.7 q4
Where it runs
Taken from the card's availability section.
Platform
Id on that platform
Hugging Face
deepcogito/cogito-671b-v2.1
Together AI
deepcogito/cogito-v2-1-671b
Verified benchmark evidence
Each row was checked against its source by a reviewer, and carries the model identifier as actually evaluated — which is not always the same as this card's.