LFM2.5 2.6B
2.7B parameters · 128k context · lfm1.0 · released 2026-07-28
chatagenticreasoning
What to run it on in Germany
Fully in memory at 32k context, priced at retailers today.
Nothing we price holds this model fully in memory.
All hardware that runs it
Everything we price, best value first. Two cards split the model by layers.
Nothing we price can run it at this context.
Memory needed
Weights, KV cache and runtime buffers at each context length (KV cache at fp16).
| Quant | File |
|---|
Run it
Copy a command for the runtime you use.
No published builds to run yet.
Notes
Text-only model under Liquid AI's custom LFM 1.0 licence ("license: other"), whose commercial terms are not stated in the card; the vendor says it is not recommended for agentic coding or knowledge-heavy tasks. Requires transformers>=5.0.0 and always emits reasoning (<think>) before answering.
Questions
- What licence is LFM2.5 2.6B released under?
- lfm1.0.