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.)
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.
I love these smaller models for the added capability they can bring to older hardware.
Recently picked up a 2013 Mac Pro (the trashcan one) on eBay for $150, and the official 6-bit quant of 2.6B runs at 25-30 tok/s under llama.cpp on one of the D500 GPUs. After installing Ubuntu LTS I have myself a lovely (if somewhat inefficient) little homelab server.
12 comments
[ 2.7 ms ] story [ 35.8 ms ] threadNote 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.
Why is Qwen3.5 2B not in the table?
Recently picked up a 2013 Mac Pro (the trashcan one) on eBay for $150, and the official 6-bit quant of 2.6B runs at 25-30 tok/s under llama.cpp on one of the D500 GPUs. After installing Ubuntu LTS I have myself a lovely (if somewhat inefficient) little homelab server.