fine-tuned LiquidAI’s LFM2.5-230M on Fable-5 coding traces - its better than I expected it to be
Summary
Fine-tuned LiquidAI's LFM2.5-230M model on Fable-5 coding traces, finding the results better than expected.
Similar Articles
LiquidAI/LFM2.5-230M
Liquid AI released LFM2.5-230M, a compact 230M-parameter hybrid model optimized for on-device deployment with fast edge inference speeds (213 tok/s on Galaxy S25 Ultra) and built for agentic tasks via reinforcement learning.
@liquidai: Introducing LFM2.5-230M: our smallest model yet, built to run fast anywhere (CPUs, NPUs, and GPUs) to enable agentic ta…
Liquid AI releases LFM2.5-230M, a small 230M parameter model optimized for fast inference on CPUs, NPUs, and GPUs, targeting agentic tasks on devices like phones and robots.
Liquid AI releases LFM2.5-8B-A1B
Liquid AI released LFM2.5-8B-A1B, an edge model with a 128K context window, 38T tokens of pre-training, and large-scale reinforcement learning, capable of tool calling and complex tasks while fitting on an entry-level laptop.
@noctus91: I recently switched from Qwen 3.5 9B to LFM2.5-8B-A1B by @liquidai, and it's quickly become my default local model in H…
A user shares their positive experience switching from Qwen 3.5 9B to Liquid AI's new LFM2.5-8B-A1B model, praising its speed and reliability for agentic tasks while noting coding remains a weakness. The model is an 8B MoE with 1.5B active parameters and 128K context, optimized for devices and server-side use.
Liquid AI reveals 8B-A1B MoE trained on 38T
Liquid AI released LFM2.5-8B-A1B, an edge MoE model trained on 38T tokens with a 128K context window, improved tool calling, and reasoning capabilities, available on Hugging Face.