LFM2.5 24B A2B
24B total, 2B active · 128k context · lfm1.0 · released 2026-10-12
chatagenticreasoningcoding
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 MoE reasoning model (24B total, ~2B active) that always emits a <think> block; requires transformers>=5.0.0. Vendor advises against knowledge-heavy use without retrieval or web search.
Questions
- What licence is LFM2.5 24B A2B released under?
- lfm1.0.