cogito:32b
Family context: Cogito v1 Preview family
Publisher: Deep Cogito
The Cogito v1 Preview release describes language models trained with Iterated Distillation and Amplification, offering direct answers or optional reflective generation.
Publisher-described context, separate from Sigma5C observations and recorded catalog statistics.
Published family information
- Initial size labels
- 3B, 8B, 14B, 32B and 70B Source
- Documented generation styles
- Direct and reflective modes Source
Publisher-described uses
- Text generation and reasoning-oriented research. Source
Reference limitations
- The family includes different upstream lineages. A generic latest tag does not identify a checkpoint or permit copying a sibling’s license. Source
A recorded tag and an upstream card association do not verify the deployed checkpoint, quantization, configured context or current hosted availability.
Publisher sources
- Cogito v1 Preview family official documentation — Deep Cogito. Checked .
Links
Recorded references do not establish downloadable weights, licensing or current availability.
32.0B
parameters
Q4_K_M
quantization
qwen2
architecture
131072
context
apache-2.0
license
2025-04-08
released
Where cogito:32b comes from
Company / lab
Deep Cogito
See every model and family from this maker.
Model family
cogito
Other versions and sizes in this line.
completiontoolsthinking