LFM2.5 2.6B model competitive with 4x larger models (huggingface.co)
86 points by nateb2022 7 days ago
lend000 6 hours ago
I can't imagine who is using something like this for agentic coding, but I see exciting opportunities on the horizon when we can have hundreds of reasonably rational and conversational agents working on local machines to simulate emergent behavior (simulating crowds, markets, ecosystems, game NPCs, etc.)
trvz 5 hours ago
Agentic behaviour isn't just coding. In fact:
> We recommend using it for agentic workloads, tool use, data extraction, RAG, and long-context workflows. It is not recommended for agentic coding and knowledge-heavy tasks.
touisteur 5 hours ago
Really curious about people's workflows with these agentic-but-not-for-coding workflows. Are there some interesting people to follow there or just good testbeds/environments to get an idea ?
dd8601fn 4 hours ago
l3x4ur1n 3 hours ago
antupis 4 hours ago
yieldcrv 3 hours ago
Gecko4072 6 hours ago
These LiquidAI models have never worked well for me in practice.
eurekin 5 hours ago
Care to share any details? I'm about to check the 2.6b lfm on document editing.
BoredomIsFun 2 hours ago
I agree. They have serious issues with coherence.
lostmsu 4 hours ago
It's not even competitive with 2x sized Qwen 4B.
Why is Qwen3.5 2B not in the table?
0xbadcafebee 5 hours ago
LFM's training/post-training is famously different than other models. They target reliable operation of tiny models in ways other model families don't (they aren't just scaling a larger model to a smaller size). If you're looking for good performance out of tiny models, LFM has the most advanced design.
Note how they're much smaller than all other models in the comparison yet match or exceed them. This is for 2.6B params, but they have models as small as 230M. Nobody else designs models that small.
woadwarrior01 5 hours ago
> Note how they're much smaller than all other models in the comparison yet match or exceed them.
There's a strong incentive to cherry pick in self-reported comparisons. If there is a model that's better, it gets left out. Have you seen Nanbeige4.2-3B or Ling-3.0-tiny?
> Nobody else designs models that small.
There are people building even smaller models.
harshshah212003 5 hours ago
Will this work in i3/i5 laptops?
zweifuss 4 hours ago
It should. With good speed even on a 12th gen Intel. But more importantly, what's your use case?
GaggiX 3 hours ago
The model is cool but I would prefer if people do not editorialize the titles on their HN submissions.