LFM2.5-2.6B-RLCD
LFM2.5-2.6B-RLCD by monotykamary is a decision model: it answers typed questions with a probability for each allowed answer instead of generating text. It scores 6.1 on the Jev Decision Index (rank 149).
Pricing
No hosted price is listed. The weights are open: the cost is your own compute.
Specifications
- Provider
- monotykamary
- Parameters
- 3B
- Released
- Sep 2026
- Open weights
- Yes
- Question types
- Choice (one of N options), Score (ordered rubric), Yes / no
- Mechanism
- Decoder LM with a decision readout
- Backbone
- LiquidAI/LFM2.5-2.6B-Base
- Jev-compatible request
- No
- Runs on CPU
- No
- License
- lfm1.0
- Hugging Face
- monotykamary/LFM2.5-2.6B-RLCD
Benchmarks
- Jev Decision IndexECE 0.255
- 6.1
Jev Decision Index: public 6.8, ECE 0.255, Brier 0.792. Lower ECE means its probabilities can be taken at face value.
Speed & latency
Compare LFM2.5-2.6B-RLCD with…
FAQ
How much does LFM2.5-2.6B-RLCD cost?
LFM2.5-2.6B-RLCD has no hosted price listed; its weights are open, so the cost is the compute you run it on.
What questions can LFM2.5-2.6B-RLCD answer?
LFM2.5-2.6B-RLCD answers choice (one of n options), score (ordered rubric), yes / no questions, returning a probability for each allowed answer.
Is LFM2.5-2.6B-RLCD well calibrated?
On the Jev Decision Index its expected calibration error (ECE) is 0.255; below about 0.05, a stated 80% confidence is right roughly 80% of the time.
Is LFM2.5-2.6B-RLCD open weight, and can it run on a CPU?
Yes, LFM2.5-2.6B-RLCD has open weights. It needs a GPU to run at useful speed.
Data as of 2026-10-14. Source: Metatext decision-model catalogue, 2026-10-14 (Jev Decision Index, Enterprise Decision Arena, Hugging Face). Pricing is per 1M tokens (USD); confirm with the provider before production use.