Liquid AI LFM3: Six Open-Weight 2B Models That Fit in 1 GB

Liquid AI released LFM3 on October 27, six open-weight models of roughly 2 billion parameters each, with the text model running in about 1 GB at 4-bit precision and every model fine-tunable on a single GPU. The release includes two decision models, d1-2B and d1-Omni-2B, which return typed answers such as probabilities, confidence-scored choices and extracted document values in a single forward pass instead of generating text. Liquid AI reported that fine-tuning LFM3-VL-2B on a few hours of training on one NVIDIA A100 raised defect-classification accuracy from under 10% to 67%, and that LFM3-VL-2B beats models of similar size by at least 7.4 points across 62 vision benchmarks while matching Gemma 4 12B.

Liquid AI shipped LFM3 on October 27 — six open-weight models, all around 2 billion parameters, covering text, vision, audio, omni, and two decision variants. The text model runs in about 1 GB at 4-bit precision. Every model is fine-tunable on a single GPU. All weights are on Hugging Face now. The size is the headline. The decision models are the actual story. The Part Most Coverage Missed: Decision Models LFM3 ships two decision models — d1-2B and d1-Omni-2B — and they work differently from every other model in the family. They do not generate text. Instead, you define a set of questions, pass them an input a support ticket, an invoice, an image, a voice note , and they return typed answers in a single forward pass: probabilities, choices with confidence scores, object pointers, extracted document values, number estimates with ranges. No output parsing. No prompt engineering to coerce a JSON response. If you are building routing logic, document extraction pipelines, content moderation, or quality inspection workflows, this is a meaningfully different primitive from a chat model. d1-2B handles text and images. d1-Omni-2B adds video and audio input. Both are built on top of their respective VL and Omni backbone variants. Liquid’s defect-classification benchmark is a useful reference point: fine-tuning LFM3-VL-2B on a few hours of training on one NVIDIA A100 took accuracy from under 10% to 67%. The fine-tune path to d1 is the same — pick a modality, fine-tune on your data, deploy locally. The Six Models | Model | Params | Input | Output | |---|---|---|---| | LFM3-1.7B | 1.73B | Text | Text | | LFM3-VL-2B | ~2B | Text, images, video | Text | | LFM3-Audio-2B | ~2B | Text, audio | Text, speech | | LFM3-Omni-2B | ~2B | Text, images, video, audio | Text, speech | | d1-2B | ~2B | Text, images | Typed answers | | d1-Omni-2B | ~2B | Text, images, video, audio | Typed answers | All six share a single base — LFM3-1.7B-Base — built on a tri-hybrid architecture: 13 gated short-convolution layers, 5 sliding-window attention layers, and 6 global attention layers across 24 blocks. The convolutions handle local pattern matching cheaply. Sliding-window attention covers mid-range context. Global attention layers handle the long view at 256K tokens. Liquid says the architecture was found via automated hardware-in-the-loop search across 14 processor classes, which explains why it runs fast on both server GPUs and edge hardware. Running LFM3 The text model in 4-bit quantization is approximately 1 GB — it fits on a phone. Liquid validated performance on Apple M5 Max, AMD Ryzen AI Max+, and iPhone 17 Pro. At 32K context, LFM3-1.7B prefills at least 2.5x faster and decodes at least 1.8x faster than all compared models on all three platforms, while using less memory. Available in every major format: GGUF for llama.cpp https://github.com/ggerganov/llama.cpp and Ollama https://ollama.com , MLX for Apple Silicon, BF16/FP8/NVFP4 for vLLM and SGLang, ONNX for ONNX Runtime, and standard Hugging Face Transformers https://huggingface.co/LiquidAI . The quickest path to running the text model: ollama run liquidai/lfm3-1.7b Or via the Hugging Face Python API: python from transformers import AutoModelForCausalLM, AutoTokenizer model = AutoModelForCausalLM.from pretrained "LiquidAI/LFM3-1.7B" tokenizer = AutoTokenizer.from pretrained "LiquidAI/LFM3-1.7B" Performance Against Larger Models LFM3-VL-2B outperforms all models of similar size by at least 7.4 points across 62 vision benchmarks and matches Gemma 4 12B — a model six times larger. LFM3-1.7B edges Gemma 4 12B on LiveCodeBench v6 73.46 vs 72.0 . Whether these benchmarks reflect your actual workload depends on what you are building, but for a 2B-class model the numbers are unusually competitive. License and Where It Fits LFM3 ships under the LFM Open License v1.0. Companies under $10M in annual revenue get royalty-free commercial use. Larger organizations need to negotiate directly with Liquid AI. It is not Apache or MIT — worth checking before you ship to production. The deployment story is strongest for teams that need on-device inference for privacy or latency, edge agents without cloud dependency, enterprise-controlled infrastructure, or structured inference pipelines where decision models replace brittle prompt engineering. Liquid provides fine-tuning notebooks for every modality. The shared backbone means specializing one variant does not require starting another from scratch. If you have been running LFM2.5-24B-A2B https://byteiota.com/liquid-ai-lfm2-5-24b-a2b-run-an-agent-model-on-your-laptop/ for agent workloads, the LFM3 text model is worth benchmarking as a drop-in replacement on constrained hardware. Weights are live on Hugging Face https://huggingface.co/LiquidAI . The full technical breakdown is on the Liquid AI blog https://www.liquid.ai/blog/lfm3 , and the Hugging Face technical post https://huggingface.co/blog/LiquidAI/lfm3 covers fine-tuning specifics for each modality.