LFM3-1.7B Benchmarks, Pricing & Rankings
Liquid AI · 2026-10-27 · Open · Current
Snapshot 2026-11-06 · updated weekly
LFM3-1.7B ranks #67 of 71 on the AMR leaderboard.
LFM3-1.7B benchmark scores
LFM3-1.7B price, speed & context
Input price
Free
per 1M tokens
Output price
Free
per 1M tokens
Speed
—
tok/s
Context
256K
tokens
About LFM3-1.7B
LFM3-1.7B is Liquid AI's open-weights on-device text model from the six-model LFM3 family (released 2026-10-27, Hugging Face release). 1.73B parameters, 256K context window, tri-hybrid architecture with an explicit reasoning mode and agentic tool-calling post-training; ~1 GB at 4-bit precision with a 1.6 GB KV cache at 128K context. Not listed on OpenRouter (only LFM2.5 serves there), so prices show 0 = open weights with no commercial API card; benchmarks are absent from all four tracked sources, so the AMR score stays unranked (provisional: excluded from ordering) rather than anchored.
Models around LFM3-1.7B in the rankings
More Liquid AI models
LFM3-1.7B FAQ
Where does LFM3-1.7B rank?
LFM3-1.7B ranks #67 of 71 tracked AI models on the AMR aggregate as of October 2026, with an aggregate score of 0.0. Its strongest dimension is AMR at 0.0.
How much does LFM3-1.7B cost?
LFM3-1.7B costs Free per million input tokens and Free per million output tokens on the standard API. At a typical 1:3 input/output agent workload, that blends to roughly $0.00 per million tokens.
What is the LFM3-1.7B context window?
LFM3-1.7B supports a 256K token context window and generates at a median 0 output tokens per second. That context fits roughly 171 standard documents in a single prompt.
Is LFM3-1.7B open source?
Yes — LFM3-1.7B ships open weights that you can download and self-host or serve through any compatible inference provider.
What is better than LFM3-1.7B?
Pixel Canary ranks one place higher at #66 with an AMR score of 38.6. LFM3-1.7B still wins 0 of the tracked dimensions head-to-head — check the comparison table to see exactly which.