LFM3 1.7B
Liquid AI LFM3 1.7B is a compact open-weight text model for on-device chat, tool use, agents, coding, and structured extraction. Its hybrid convolution and attention architecture supports a 256K-token context, while official GGUF and MLX variants make it practical on CPUs, Apple Silicon, and smaller GPUs.
Task Fit
Not marked for typed decisions in the current library.
Tool use, repo work, terminal workflows, and coding benchmarks.
Code generation, debugging, refactoring, and benchmark signal.
General writing, Q&A, and assistant use.
Document QA benefits from long context and instruction following.
Not marked for vision in the current library.
Not marked for image generation in the current library.
Not marked for video generation in the current library.
Not marked for voice in the current library.
Evidence level
How this is assessed →Memory and hardware-fit values are planning estimates unless a tested report is linked.
Variants and Quant Artifacts
Choose the artifact first; hardware fit follows from RAM, VRAM, format, and runtime.
| Quant | Format | Quality | Min RAM | Reco RAM | Runtime | Action |
|---|---|---|---|---|---|---|
| Q4_K_M | gguf | balanced | 4GB | 8GB | transformers, vllm, llama.cpp, lm-studio, mlx | Plan with this |
Recommended Hardware
Lowest estimated 5-year cost that can run this model.
Enough unified/system memory with a balanced 5-year cost.
Highest local performance signal among compatible hardware.
Benchmarks
No benchmark data is available for this model yet.
Sources and compatibility
Execution evidence
Run LFM3 1.7B with a documented recipe
Recipes connect hardware, a model artifact, tools, settings, verification, and a reportable result.
No verified recipe is linked to this record yet.
Compatibility estimates remain available in the planner. A recipe appears here only after its exact stack and verification protocol are documented.
Similar Models
Liquid AI LFM3 Omni 2B is a 2.17B edge-focused any-to-any model that accepts text, images, video, and audio, then outputs text, speech, or interleaved text and speech. It supports a 32K-token context, video-with-sound understanding, speech interaction, and official BF16 and GGUF deployment paths for local devices.
Liquid AI LFM3 VL 2B is a 1.92B on-device vision-language model for images, documents, charts, app screens, spatial reasoning, and video understanding. It supports a 128K-token context and official GGUF, MLX, ONNX, and OpenVINO variants. Liquid AI does not position it as a coding or complex multi-turn reasoning model.
Liquid AI LFM2.5 24B-A2B is a 24B-total, 2B-active reasoning MoE built for fast private agents on-device. It provides a 131K-token context, improved multilingual tokenization, tool-oriented post-training, and official native and GGUF checkpoints.