Model Detail Evidence reviewed

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.

Liquid AILFM3lfm1.02026-10-27
Parameters
1.73B
Dense model
Context window
262K
Long context
Architecture
lfm3 hybrid convolution attention
dense
Quality score
88
Planner signal

Task Fit

Typed DecisionsNot a fit

Not marked for typed decisions in the current library.

Code AgentSupported

Tool use, repo work, terminal workflows, and coding benchmarks.

CodeSupported

Code generation, debugging, refactoring, and benchmark signal.

ChatSupported

General writing, Q&A, and assistant use.

RAGSupported

Document QA benefits from long context and instruction following.

VisionNot a fit

Not marked for vision in the current library.

Image GenerationNot a fit

Not marked for image generation in the current library.

Video GenerationNot a fit

Not marked for video generation in the current library.

VoiceNot a fit

Not marked for voice in the current library.

OverallStrong coverage
ParametersCurated source
Task fitCurated source
MemoryArtifact metadata
LicensePublished source
BenchmarksNot available
Hardware fitCalculated

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.

1 artifacts
QuantFormatQualityMin RAMReco RAMRuntimeAction
Q4_K_Mggufbalanced4GB8GBtransformers, vllm, llama.cpp, lm-studio, mlx Plan with this

Benchmarks

No benchmark data is available for this model yet.

Sources and compatibility

Hugging FaceLiquidAI/LFM3-1.7B
OllamaNot mapped
EvidenceEvidence reviewed
Artifact sourceOfficial model weights
Default variantLFM3 1.7B Coder
Tool callingSupported

Execution evidence

Run LFM3 1.7B with a documented recipe

Recipes connect hardware, a model artifact, tools, settings, verification, and a reportable result.

Browse all recipes →

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

Continue planning your local AI setup