Liquid AI's 24B model with just 2B active parameters beats larger MoEs on agentic tasks
LFM2.5-24B-A2B: Built for Fast On-Device Agents
Liquid AI released LFM2.5-24B-A2B, a 24B-parameter reasoning model with only 2B active parameters per token, built for fast on-device agents. It matches or beats Qwen3.6-35B-A3B on five of eight agentic benchmarks, including a 3x win on AutomationBench, while decoding 184 tokens/s on an Apple M5 Max and over 21K output tokens/s on a single NVIDIA B300 GPU. The open-weight model is available on Hugging Face and supports llama.cpp, MLX, vLLM, SGLang, and ONNX.
More surprisingly, it even figured out it was in a sandbox.
- sebmellen
> it runs up to 1.7× faster than comparable MoEs on-device, with 184 tokens/s on an Apple M5 Max and up to 21K output tokens/s on a single NVIDIA B300 GPU
Wow, those are seriously impressive numbers for how intelligent this model seems to be!
One thing that this article doesn't clarify, and that I guess I really should look into, is what exactly AutomationBench tests for as compared to other benchmarks. The standout performance on AutomationBench is interesting to see, but I don't know what it really means because the model seems to score relatively close to other local models on every other benchmark.
- ghotli
Maybe someone knows what order of cost a release like this requires in real terms of hardware and energy spend?
The cost over the diff from the moment of beginning training to the end. It's iterative from a prior model so it starts there and becomes this release after spending occurs I presume.
For example, is liquid spending millions in energy in this case and the cost is amortized over successive training runs over the initial datacenter spend? What if it's just eating cloud costs and has no dedicated hardware, that sort of thing. I don't particularly mean this model and liquid specifically. Just for this class of smaller fast on-device range of model what is the order of the training cost in real terms?
Maybe its short sighted to ask it as if it's a singular training run and is perhaps the end state of many variations of testing thus all of the R&D training runs would have to be included to to inform what became the final release. Seems like this should be taken into consideration. If anyone happens to know it'd be appreciated!
- 2001zhaozhao
This seems like a big deal, no?
If Qwen had released a Qwen3.8 MoE of similar size, with a naive extrapolation its capabilities would roughly be similar to this model. So basically someone has caught up to Qwen (albeit Qwen from 1-2 months ago) in parameter efficiency.
- effortprogramme
Always good to hear for on-device suited model, but always cannot sure how it real-performance in real task..
- MatthiasPortzel
Very cool. I’ve been on Gemma 4 12B because of my limited RAM. There’s already an Unsloth quantization of this model so I’m downloading that and will check its performance in the morning. Someone else in this thread recommended Ternary-Bonsai-27B, which I’ll also try.
Just also wanted to note that this model has a questionably-enforceable non-commercial use clause in its license. I really wish they had consulted with an IP lawyer, it’s very confusing.