Dataset updated 2026-10-30

LFM3 1.7B

LFM3 1.7B loads in 1.1 GB at Q4_K_M, comfortably from 8 GB of memory, Macs included, starting at the Mac Mini M6 16GB. Below is the memory math we ran for it, the smallest card that fits, and the fastest machine we track.

Parameters: 1.73B
Format: Q4_K_M
Min memory: 4 GB
Best for: Local agents, Tool calling, Structured output

Memory math

How much memory does LFM3 1.7B need?

LFM3 1.7B is a 1.73B dense model built for local agents, tool calling, structured output. The weights alone take 1.1 GB at Q4_K_M; add context and the OS, and it belongs in the 8 GB memory class. Every number below comes from the ModelFit engine: speeds are estimates, labeled est., because we do not benchmark hardware ourselves.

Weights (Q4_K_M)

1.1 GB

+ KV cache (16k)

~0.2 GB

Total at 16k

~1.3 GB

Comfortable from

8 GB

KV = fp16 estimate (q8_0 cache roughly halves it). "Comfortable" = weights + KV within the engine's tiered budget (~70-85% of memory).

Hardware snapshot

Which machines run LFM3 1.7B?

Smallest GPU: NVIDIA GeForce RTX 4060est. 159 tok/s · 8 GB VRAMtypical error 10%
Fastest: NVIDIA GeForce RTX 5090est. 484 tok/stypical error 10%
Runs on a Mac?: Mac Mini M6 16GBest. 109 tok/stypical error 5%

Verdicts come from the same engine that powers our fit checker: memory capacity first, bandwidth for speed. How we compute these numbers · What typical error means · Hugging Face model card

Get told when a better model fits your MacBook Air M5 16 GB

Get one email when a new open-weight model is a better fit for this machine.

For: MacBook Air M5 16 GB

You'll also get the weekly ModelFit email. By signing up you agree to our Privacy Policy. Unsubscribe from either email anytime, in one click.

Frequently asked questions

How much memory does LFM3 1.7B need?

1.1 GB for the Q4_K_M weights, plus ~0.2 GB of KV-cache at 16k context, about 1.3 GB total. Comfortable from 8 GB of VRAM or unified memory.

Does LFM3 1.7B run on a Mac?

Yes, from the Mac Mini M6 16GB (est. 109 tok/s, typical error 5%). Unified memory means the RAM budget is the only limit.

What is the smallest GPU for LFM3 1.7B?

The NVIDIA GeForce RTX 4060 (8 GB VRAM) is the smallest tracked card that runs LFM3 1.7B comfortably, est. 159 tok/s, typical error 10%.

Cite this page

ModelFit: LFM3 1.7B, specs, memory math and hardware verdicts.
https://modelfit.io/models/lfm3-1.7b (dataset updated 2026-10-30, CC BY 4.0).