What hardware do you need to run LFM3 1.7B?

LFM3 1.7B at Q4_K_M is 1.1 GB of weights, with a context ceiling of 256k tokens. Liquid's new generation and the smallest download on this list: a dense 1.73B post-trained for local agents and tool calling, in 16 languages. Liquid says to use retrieval for anything knowledge-heavy and not to reach for it for agentic coding or long chains of reasoning. On the cheapest machine that runs it, a Mac mini M6, 16GB, it generates 76 tok/s at 32k of context, worked out from memory bandwidth.

How good is LFM3 1.7B, really?

It has not been placed on the intelligence index yet. See the whole table.

What LFM3 1.7B costs either way

Nobody rents LFM3 1.7B by the token. The closest hosted match, Granite 4.2 8B, costs $0.06 per million input tokens and $0.15 per million output (OpenRouter, cheapest active endpoint, checked 2026-10-28). Buying a machine only beats that if you use it hard enough, for long enough, that the hardware price divides down below the rental bill. What a million tokens costs each way puts the two prices side by side.

Machines that run LFM3 1.7B

Every machine here holds it to 256k, which is this model's own ceiling and the longest the calculator offers, so the choice between them is speed and price rather than how much you can keep in the window.

All 56 machines on this site run it at 32k, not just the eight in the table. One table sets every machine against the others: price, the memory its GPU can use, what it holds and how long it takes to pay for itself.

One machine per family, cheapest first. Speeds are measured where a public benchmark exists and estimated from memory bandwidth otherwise; the calculator says which for any configuration. The longest context is the longest setting the calculator offers that the machine still holds this model at, cache included, and no machine is shown taking it past its own 256k limit. Each one opens the calculator on that machine at that length.

For scale, the calculator starts from 80 tok/s for a hosted API and times a local machine against it. 5 of the 8 above reach it, and the slowest is 76 tok/s.

The cheapest machine that runs it is sold with 16 GB. There is a page on what 16 GB runs, machine by machine: it names the 6 machines here sold at that size, and the 15 current models the roomiest of them holds at 32k, this one among them.

It fits in less memory than that: the smallest size here that runs it at 32k is 12 GB, on the GeForce RTX 3060, 12GB at $329, card only, which hands a model 11 GB and is no longer sold.

Run LFM3 1.7B at 256k on the Mac mini M6, 16GB

How much memory does LFM3 1.7B need at 256k?

Every figure above is priced at 32k of context. At 256k, which is this model's own ceiling and the longest the calculator offers, LFM3 1.7B needs 4.3 GB rather than 1.5 GB. The weights are the same either way; the key-value cache goes from 0.4 GB to 3.2 GB.

The window costs nothing in hardware: all 37 machines here still sold at a published price hold LFM3 1.7B at both lengths, and the cheapest of them is the Mac mini M6, 16GB at $899.

On the Mac mini M6, 16GB it runs 76 tok/s estimated at 32k and 27 tok/s estimated at 256k. Every token generated reads the whole cache back, so a longer window is slower as well as bigger.

The specifics

Parameters

1.7B

Quantisation

Q4_K_M

Weights on disk

1.1 GB

KV cache

0.4 GB at 32k context — Three kinds of layer in 24: 13 gated short convolutions that keep a fixed-size state, 5 sliding-window attention capped at 256 tokens, and 6 global attention. Only those 6 grow with the context, so the whole 256k window costs 3.2 GB of cache against 1.1 GB of weights. How weights and cache add up.

Maximum context

256k tokens

Licence

LFM 1.0 (see repo)

Sources

LiquidAI/LFM3-1.7B, LiquidAI/LFM3-1.7B-GGUF