meituan-longcat/LongCat-2.5-W4A4
archived · low-signalmodel
LongCat-2.5 is a native multimodal MoE model for long-horizon agentic tasks, with 1.6 trillion total parameters and approximately 48 billion activated per token. Mixture-of-experts, 495B total (768 experts). Context: 512K tokens (config). License: mit.
- Org
- meituan-longcat
- Released
- 2026-11-04
- Status
- archived · low-signal
- License
- mit (permissive)
- Parameters
- 494.8B
- Architecture
- MoE · 768 experts, None/token · LongcatCausalLM
- Context
- 524,288 tokens (config.json)
- Task
- image-text-to-text · vision
- Signal
- 3 HF likes · 240 downloads
- Archived
- 2026-11-13 (no longer listed by the collector; stats as last seen)
Runs on
estimate from params; need = weights + FP16 KV cache for 8K tokens + 1GB. A sizing calculation, not tested.
- Q4 ~340.0 GB (estimated size): Mac 512GB
- Q8 ~568.9 GB (estimated size): no listed device
- FP16 ~1032.8 GB (estimated size): no listed device
Links
First published here 2026-11-04 · updated 2026-11-13 · markdown · JSON