LFM2.5 VL 3B
3.1B parameters · 32k context · lfm1.0 · released 2026-08-11
chatvisionagentic
What to run it on in India
Fully in memory at 8k 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
Optimized for single-turn, low-latency tasks such as OCR, grounding and object detection; not recommended for long-context, reasoning-intensive tasks. Transformers quick start requires transformers>=5.0.0.
Questions
- What licence is LFM2.5 VL 3B released under?
- lfm1.0.