Introducing LFM3: Every Modality for Specialized Intelligence

Today, we’re excited to announce LFM3, our new generation of Liquid Foundation Models (LFMs) built for specialized intelligence. The LFM3 model family is multimodal by nature and brings text, vision, audio, omni, and decision models onto one new shared backbone. The first release of the LFM3 family covers models in the 2B parameter range.

Built on a new hybrid architecture and 22T tokens of pre-training, LFM3 is far more expressive than LFM2 while maintaining its efficiency. The extra capacity in a small, fast model makes LFM3 the ideal starting point in its class for specialized intelligence: this is because it can be fine-tuned locally, it can run on any device, and it is capable enough to become a reliable expert on a specialized task.

The base and post-trained models are open-weight and available today on Hugging Face, our Playground, and the Liquid AI API. Check out our docs on how to run and fine-tune them locally.

Download weights

Try in Liquid API

Try in Playground

Benchmark in Pipette

New architecture for more expressivity

LFM2 showed that a hybrid of short convolutions and attention could run fast on-device without sacrificing quality. Its design came from our automated hardware-in-the-loop architecture search. For LFM3, we used this search to redesign that architecture for agentic use cases, which need more capability per parameter and fast inference over long contexts.

We also expanded the hardware in the loop, from CPUs in one phone and one laptop for LFM2 to 14 device and backend combinations for LFM3: phones (Samsung Galaxy S26 Ultra and OnePlus 15), a Raspberry Pi 5, laptops (Apple M4 Max and AMD Ryzen AI), and Arm and x86 cloud CPUs, plus GPUs and the Qualcomm Hexagon NPU.

Gated short convolutions still make up over half the layers. To add capability without slowing down long contexts, we tried swapping some of them for other sequence blocks, and sliding-window attention (SWA) gave the best quality–speed tradeoff. We kept the other changes described below only where they improved quality without a meaningful speed cost. The payoff shows at long context. Per parameter, LFM3-1.7B matches LFM2-1.2B on short prompts across edge devices, and with 8K tokens in context it is about 25% faster.

Tri-hybrid layer mix. LFM3 combines three operators: gated short convolutions, sliding-window attention (SWA), and global attention. Of its 24 layers, 13 are convolutions, 5 are SWA with a 256-token window, and 6 are global attention. The convolutions also use a kernel size of 7, up from 3 in LFM2.

Head-wise gated attention. A sigmoid gate scales each head’s output, so a head can switch off when it has nothing to add. This can help suppress activation outliers that hurt quantization and improve training stability.

Partial RoPE. Global attention layers rotate only the highest-frequency half of each head and leave the low-frequency half unrotated, so those dimensions match on content regardless of distance. SWA layers keep full RoPE.

Sandwich norm. Each block normalizes both its input and its output, which helps keep activations well-scaled.

LFM3 uses the same 128K vocabulary as LFM2.5-8B-A1B, built to tokenize non-Latin scripts more efficiently.

Training. LFM3-1.7B-Base was pre-trained on 22T tokens. Compared with LFM2, the mix adds more scientific papers, repository-level code, a wider range of knowledge sources, and considerably more math. The final 3.5T tokens are a mid-training stage on curated, higher-quality data, with a larger share of agentic traces and diverse tool calls to prepare the model for agentic post-training. This stage also extends the context window to 256K tokens.

A multimodal family for every need

The first LFM3 release includes six models, all branched from the same LFM3-1.7B-Base backbone and all around 2B parameters. Four of them cover different input modalities (text, vision, audio, and omni), and the last two are decision models specialized from the vision and omni models. Instead of running one large general-purpose model, you can pick the one that fits your use case, customize it, and run it on-device.

For a deeper dive into the performance and inference results behind these models, refer to the respective model cards.

As AI increasingly moves from the cloud to the client, developers need models that can be deployed efficiently across the broad spectrum of AI PCs. Liquid AI's LFM3 family combines strong multimodal capabilities with a compact footprint that is well suited for on-device AI experiences. AMD has worked closely with Liquid AI across multiple generations of models, and we're excited to see LFM3 expand what's possible for specialized AI applications running locally on systems with AMD Ryzen™ AI processors.

Across industries, we’re seeing edge AI evolve from running dedicated detection and perception models to supporting multiple concurrent AI workloads, including vision-language models, natural-language interfaces and multimodal reasoning. The challenge is delivering these capabilities within the compute, memory, and power constraints of edge devices. LFM3 brings text, vision, and audio together in a unified architecture designed for efficient deployment, with open weights that developers can fine-tune for specific applications. Developers can already run Liquid AI’s LFM2.5-VL models on Ambarella silicon through the Cooper Model Garden, and we have begun enabling LFM3 on the same platform.

The next generation of AI will be more multimodal, personalized, and private while being distributed across devices and the cloud. Liquid AI’s LFM3 family is an exciting step in that direction, and we’re pleased to work together to bring fast, efficient, and innovative AI experiences to devices powered by Snapdragon® processors.

Text

LFM3-1.7B is a text model for local agents and specialized applications with a 256K-token context window.

It is post-trained to run in agentic harnesses such as Hermes Agent, Pi, and OpenClaw. It can triage your inbox, manage your calendar, research topics on the web, send you morning briefings on WhatsApp, and use tool search to find the right tool among thousands of options. Since tokens are free, dozens of agents can run continuously in the background. You can adapt it to your domains, harnesses, and tools with a short fine-tuning run on a single GPU.

Benchmark	LFM3-1.7B (1.7B)	LFM2.5-2.6B (2.6B)	MiniCPM5 2B (2.5B)	Gemma 4 E4B (8B)	Qwen3.5 4B (4.7B)	Qwen3.5 9B (9.7B)
Agents
LiveClaw	45.60	14.70	30.37	20.36	19.94	35.77
Claw-Eval General (EN), average	68.64	62.63	60.74	56.14	61.96	66.53
Claw-Eval General (EN), pass^3	51.40	37.52	34.58	22.43	42.99	51.87
BrowseComp-Plus (OpenClaw subset)	37.00	26.33	16.83	21.00	24.67	38.00
WebArena-Verified	38.42	3.02	9.11	17.06	21.92	28.94
EnterpriseOps-Gym	28.20	7.94	13.41	9.86	25.96	28.97
AutomationBench (public)	41.29	0.94	4.71	1.92	8.67	15.10
Tool use
BFCL V4	71.39	55.89	62.65	48.25	55.12	62.83
ToolSandbox	80.36	78.04	68.16	69.27	75.40	76.41
MCP-Atlas	32.57	16.45	26.38	6.19	41.37	42.67
τ³-bench	68.01	56.77	69.44	33.53	65.98	67.11
Agentic coding
SWE-bench Verified (OpenCode)	43.40	18.00	34.80	0.50	41.20	51.20
SWE-bench Multilingual (OpenCode)	23.00	8.00	15.67	0.67	23.33	35.00
Terminal-Bench 2.1 (OpenCode)	12.92	0.00	5.62	0.00	13.48	17.98
Coding
LiveCodeBench v6	73.46	60.57	70.52	71.00	61.99	69.86
LiveCodeBench Pro 25Q2	31.74	19.16	29.34	29.94	24.25	34.43
SciCode	28.47	16.32	27.78	25.00	23.02	31.60
Instruction following
IFEval	96.66	95.39	87.83	90.02	92.52	92.08
IFBench	73.03	60.48	62.08	44.56	38.16	48.84
IFStruct	93.72	82.18	72.65	78.45	87.05	89.20
Multi-IF	89.10	84.80	73.19	81.03	80.32	84.44
Knowledge
GPQA Diamond	63.37	57.78	65.15	57.88	75.76	80.40
Humanity's Last Exam (no tools)	7.17	5.88	8.20	4.77	12.84	16.41
Humanity's Last Exam (with tools)	13.90	9.60	11.50	6.00	11.60	17.50
AA-Omniscience (public)	0.50	-33.17	-5.00	-15.33	-57.17	-28.00
AA-Omniscience accuracy (public)	7.07	8.75	9.13	9.83	15.67	13.17
AA-Omniscience non-hallucination (public)	92.93	53.69	84.44	72.09	13.64	52.59
Long context
AA-LCR	52.83	6.00	49.34	39.33	52.67	62.00
RULER 128K	65.56	1.15	37.96	18.82	84.63	87.11
Average	49.37	31.55	39.19	31.74	39.27	47.24

On agentic tasks, LFM3-1.7B competes with models several times its size. It leads on instruction following and function calling on BFCL and ToolSandbox, and beats Qwen3.5-9B on long tasks in browsers and business apps (WebArena-Verified, AutomationBench). Larger models still win on agentic coding and knowledge, where size matters most, but search helps close the knowledge gap, nearly doubling its score on Humanity's Last Exam.

To achieve these results, the model went through four stages of post-training:

• Supervised fine-tuning (SFT): 1.75T tokens across various tasks, including chat, reasoning, tool calling, and agentic traces.
• Mixed reinforcement learning: many domains trained at once, from math and code to SQL and structured outputs. A length penalty in the reward keeps answers concise.
• Multi-domain on-policy distillation (MOPD): six specialist RL teachers (code, math, tool use, long context, agentic work, and enterprise workflows) are distilled back into a single model.
• Agentic RL: tasks from web browsing to office work are run inside real agent harnesses, preparing the model for deployment.<