LFM3-1.7B on Pi 5

Snapshot 2026-10-27 · ai-tier

Raspberry Pi 5 · 16 GB RAMAll performance measurements are for this device.

Capability shows how well the model answers the benchmark questions. Speed, response time and memory are measured on Raspberry Pi 5 · 16 GB.

Capability summarises instruction following, tool calling and finding information in long prompts. Speed and memory refer to the Raspberry Pi 5. — means unavailable.
Model	Capability / 100	Output tok/s	Prompt tok/s	First token · s	Task time · s	Peak memory · MiB	Parameters · B
LFM3-1.7BQ4_K_M · 4,096 context · reasoning off	48	10.3	55.8	7.4	33.7	2,285	1.7

Benchmark breakdown

Instruction following · IFEval	Tool calling · BFCL	Finding information · RULER
77	34	33

Test configuration

Model publisher: Liquid AI
Model parameters: 1.729 billion total
Published input support: text (metadata; not device validation)
Quantization: Q4_K_M
Context capacity: 4,096 tokens
Reasoning mode: off
CPU threads / parallel requests: 4 / 1
Temperature / seed: 0 / 42
Measurement date: 2026-10-27T18:34:44.213313+00:00
Result ID: split-f6e21a62c909b8d1244e
Runtime revision: 19ff817fb25e9a1b838b1d7f9f4325f7bf9779c4
Artifact repository / revision: LiquidAI/LFM3-1.7B-GGUF / b3f2ae5d73cd3c91bf40e8ba752c648aa05dffdf
Artifact SHA256: 3793e1e6e2266919d6e015287221b41100175a98eddaba92e111aed3b05c93c4
Dataset revision: a0fc00b6a07455d1efb70cc19d5ca94c5923c5261a0b41095083a41a1592a1f6
Configuration identity: 3abb93331e121da9819bdd6d937ce47d7c3db1236cb13604f6b6080532bd74cb

Measurement limits

Speed tests read 256 input tokens and generate 128 output tokens, repeated ten times. The output speed test starts without a long conversation history. Answer time uses six fixed prompts with up to 128 output tokens, repeated three times. First-text time is measured from the application making the request. Peak memory includes the loaded model; it excludes other applications on the device. Longer prompts may need more memory. Capability uses a fixed selection of public questions, rather than the full official benchmarks.

All Pi 5 measurements Methodology Publisher model card ↗Pinned engine source ↗

Measured 2026-10-27T18:34:44.213313+00:00.