Colqwen2 v1.0 vs Colqwen2.5 v0.2
No benchmarks in this slice.
Specs
| Spec | Colqwen2 v1.0 | Colqwen2.5 v0.2 |
|---|---|---|
| Context | 33K | 128K |
| Weights | Open | Open |
| Released | Nov 2025 | Jan 2025 |
| Max input | 33K tokens | 128K tokens |
| Languages | en | en |
| Memory (4-bit) | 1.3 GB | 1.8 GB |
| Licence | Apache-2.0 | Apache-2.0 |
| Commercial use | Allowed | Allowed |
What breaks when you switch
Colqwen2 v1.0 → Colqwen2.5 v0.2
Re-embed your whole corpus›
Vectors from different models can't be mixed.
Memory (4-bit): 1.3 GB → 1.8 GB
Colqwen2.5 v0.2 → Colqwen2 v1.0
Re-embed your whole corpus›
Vectors from different models can't be mixed.