DCKV learns end-to-end compression of hybrid-model prompt KV caches
On Qwen3.5-2B, tokens use over 55 times fewer bytes than bf16 with at most 1.8 points lost on three long-context benchmarks.
42
AI model
Qwen3.5-2B
- Mentions · 7d1
- Mentions · 30d2
- All mentions2
- First seenOct 7, 2026
- Last mentioned3d ago
Timeline
2 articles · newest firstStrands Decider 2B: a small, open-source, decision model
Strands Labs released Strands Decider 2B, a 2-billion-parameter open decision model fine-tuned from Qwen3.5-2B.
44
Appears with
- Strands Decider 2Bai model · 1
- Alibabavendor · 1
- TypeSafe AIorganization · 1
- Jevai model · 1
- Strands Labsorganization · 1
- Strands Harnessproduct · 1
Entities are extracted by the model from each article. First seen , last mentioned . Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.