LFM2.5-2.6B.
LFM2.5-2.6B is a compact reasoning model from Liquid AI. It is suited for agent workflows, data extraction, RAG, and long-context processing. Liquid advises against using it for agentic coding or...
1× Nvidia GeForce GTX 1660 Super · $0.030/hr.
Most-aggressive quantisation we have a working recommendation for. Lower precision = less VRAM = cheaper hardware, at a small accuracy cost.
Variants in the LFM family.
Cheapest hardware per quantisation.
Each row is one quantisation tier (the same weights compressed differently). Lower precision → lower VRAM → cheaper hardware, at the cost of small accuracy loss. $/hr is the cheapest rate on offer now. A multi-card setup uses a real instance of that size when one is rented; otherwise it is the single-card rate times the count.
| Quantisation | Cheapest GPU config | Total VRAM | Live $/hr | tokens/sec | |
|---|---|---|---|---|---|
|
FP16
FP16 — half precision (default)
|
12 GB |
$0.038/hr
Nosana · on-demand
|
46.7 | Compare → | |
|
FP8
FP8 — 8-bit float (Hopper / Blackwell)
|
6 GB |
$0.030/hr
Clore.ai · on-demand
|
87.2 | Compare → |
What it costs per month across providers.
Estimate your monthly bill for LFM2.5-2.6B across every host that publishes per-token pricing. Slide your token volumes; the chart + table re-rank cheapest-first.
No priced API access rows on file for LFM2.5-2.6B yet.
Rent the GPU instead of paying per token.
For an open-weights model like LFM2.5-2.6B, you can rent a GPU and serve inference yourself. The math: cheapest GPU rental × 730 hours/month. Power is included in a rental's hourly price.
Assumes the GPU runs 24/7 at ~85% utilisation. If your traffic is bursty, you'll pay less for the API and probably more for the GPU (idle hours still cost rental). The breakeven analysis lives on the Self-host vs API breakeven tool.