LFM2-2.6B-Exp

RL-only post-trained 2.6B model with improved math and reasoning capabilities

← Back to Text Models

LFM2-2.6B-Exp is an experimental checkpoint of LFM2-2.6B with RL-only post-training, delivering improved performance on math and reasoning benchmarks. Use this model when you need stronger analytical capabilities.

HFGGUF

Specifications

Property	Value
Parameters	2.6B
Context Length	32K tokens
Architecture	LFM2 (Dense)

Math & Logic

Strong arithmetic and logical reasoning

On-Device

Runs on phones and laptops

Fine-tunable

TRL compatible (SFT, DPO, GRPO)

Quick Start

Transformers

llama.cpp

vLLM

SGLang