Today, we're releasing LFM2.5-8B-A1B, a device-optimized model designed to power real-life applications on phones, laptops, PCs, robots, and fast & lightweight server-side use-cases.
> 8B MoE, 1.5B active
> Expanded 128K context
> LFM2.5 flagship hybrid MoE architecture
>
We're celebrating an exciting milestone in our partnership with @Shopify : our LFMs have now processed 1 billion requests on Shopify’s platform!
Read more about our multi-year partnership here: liquid.ai/blog/liquid-ai…
"Imagine it's not tokens that are actually important, it's just the outcome that actually matters."
@liquidai CEO Ramin Hasani (@ramin_m_h) reacts to Palantir CEO Alex Karp's recent viral CNBC interview:
" That was incredible. I fully agree with him."
"I like that he said,
We're celebrating an exciting milestone in our partnership with @Shopify : our LFMs have now processed 1 billion requests on Shopify’s platform!
Read more about our multi-year partnership here: liquid.ai/blog/liquid-ai…
We're celebrating an exciting milestone in our partnership with @Shopify : our LFMs have now processed 1 billion requests on Shopify’s platform!
Read more about our multi-year partnership here: liquid.ai/blog/liquid-ai…
We're celebrating an exciting milestone in our partnership with @Shopify : our LFMs have now processed 1 billion requests on Shopify’s platform!
Read more about our multi-year partnership here: liquid.ai/blog/liquid-ai…
Liquid AI (@liquidai) CEO Ramin Hasani (@ramin_m_h) says: "We're bringing the cost of tokens to zero."
"The axis was maximizing intelligence at all costs."
Foundation models need to optimize across 3 axes:
1.) Intelligence and capability
2.) Efficiency and cost
3.) Substrate:
Liquid AI (@liquidai) CEO Ramin Hasani (@ramin_m_h) says: "We're bringing the cost of tokens to zero."
"The axis was maximizing intelligence at all costs."
Foundation models need to optimize across 3 axes:
1.) Intelligence and capability
2.) Efficiency and cost
3.) Substrate:
We are at @icmlconf 2026 in Seoul. Booth B116.
We're hiring globally, including post-training and applied ML roles in our Tokyo office. Stop by our booth to talk!
私たちはICML 2026（ソウル）のブースB116に出展しています。
Today we release Antidoom, an open-source method that removes a common failure mode in reasoning models: the doom loop.
Doom-loop rates before and after, with eval scores up across the board:
> Early LFM2.5-2.6B checkpoint: 10.2% → 1.4%
> Qwen3.5-4B: 22.9% → 1% (greedy
Today we release Antidoom, an open-source method that removes a common failure mode in reasoning models: the doom loop.
Doom-loop rates before and after, with eval scores up across the board:
> Early LFM2.5-2.6B checkpoint: 10.2% → 1.4%
> Qwen3.5-4B: 22.9% → 1% (greedy
An open-source fix for one of the most common reasoning model failure modes.
One of the biggest AI trends this year isn't larger models. It's systematically removing failure modes.
Reasoning models sometimes get stuck repeating the same token sequence ("Wait...", "So...",
Today we release Antidoom, an open-source method that removes a common failure mode in reasoning models: the doom loop.
Doom-loop rates before and after, with eval scores up across the board:
> Early LFM2.5-2.6B checkpoint: 10.2% → 1.4%
> Qwen3.5-4B: 22.9% → 1% (greedy
Today we release Antidoom, an open-source method that removes a common failure mode in reasoning models: the doom loop.
Doom-loop rates before and after, with eval scores up across the board:
> Early LFM2.5-2.6B checkpoint: 10.2% → 1.4%
> Qwen3.5-4B: 22.9% → 1% (greedy
