The AI arena is free today

Open Superagent
Liquid AIReleased on Oct 27, 2026

LFM3-1.7B: Benchmarks, Pricing & Context Window

LFM3-1.7B is a language model from Liquid AI, released in October 2026.

LFM3-1.7B is Liquid AI's open-weight 1.73B text model for local agents and specialized applications, the text post-trained checkpoint of the LFM3 family (Oct 27, 2026). New tri-hybrid architecture: 24 layers (13 gated short convolutions, 5

LFM3-1.7B benchmarks

Capability tiers

Standing within each category, adjusted for leaderboard depth.

Real tasks performance

High-confidence performance for LFM3-1.7B across real-world prompt categories. Only 95% intervals at most 4 points wide are shown.

Performance by conversation depth

How LFM3-1.7B holds up as conversations get longer.

Quality Tracker

LFM3-1.7B Performance Across Datasets

Scores sourced from the model's scorecard, paper, or official blog posts

LLM Stats Logollm-stats.com - Mon Nov 02 2026
Notice missing or incorrect data?

LFM3-1.7B model size

LFM3-1.7B has 1.7 billion parameters and was trained on 22 trillion tokens. See how it compares to other models in the same parameter range.

ParametersTraining tokens
1.7B
22Ttokens
12717× tokens-to-params ratio
Small (<3B)
1.7B
1B7B70B405B

Try now

huggle
LFM3-1.7Bin Huggle

Make it with
LFM3-1.7B.

LFM3-1.7B

LFM3-1.7B latency

LFM3-1.7B time to first token, sustained output throughput, and failed-request rate from live model usage over the trailing 7 days.

LFM3-1.7B examples

Recent arena outputs from LFM3-1.7B, picked from the highest-ranked matchups.

LFM3-1.7B license

LFM3-1.7B is released under the LFM Open License v1.0 license, which permits commercial use, has 1.7B parameters.

License
LFM Open License v1.0
Commercial use allowed
Parameters
1.7B

Liquid AI LFM Open License v1.0 — open weights with a commercial-use threshold (annual revenue $10M+ requires a separate commercial license; qualified non-profits exempt for non-commercial/research use).

LFM3-1.7B resources

Official sources for LFM3-1.7B: official playground, official launch post, model weights.

LFM3-1.7B vs other models

The most-compared alternatives to LFM3-1.7B are Nemotron Nano 9B v2, DeepSeek R1 Distill Qwen 32B, Sarvam-105B. Open any pair side-by-side for benchmarks, pricing, context, and latency.

Models like LFM3-1.7B

Models ranked just above and below LFM3-1.7B by LLM Stats score.

 

Nemotron Nano 9B v2

Score pending
 

DeepSeek R1 Distill Qwen 32B

Score pending
 

Sarvam-105B

Score pending
 

Qwen3.7-Plus

Score pending
 

DeepSeek-V3

Score pending
 

Gemini 2.0 Flash

Score pending

FAQ

Common questions about LFM3-1.7B.

When was LFM3-1.7B released?

LFM3-1.7B was released on October 27, 2026 by Liquid AI. This is the official LFM3-1.7B release date tracked on LLM Stats.

How big is LFM3-1.7B?

LFM3-1.7B has 1.7 billion parameters. It was trained on 22.0 trillion tokens. It ships as an open-weight model, so you can download and run it on your own hardware.

Who created LFM3-1.7B?

LFM3-1.7B was created by Liquid AI.

What is the license for LFM3-1.7B?

LFM3-1.7B is released under the LFM Open License v1.0 license. This is an open-source / open-weight license that permits self-hosting.

Where is the LFM3-1.7B paper or technical report?

LFM3-1.7B has a paper or technical report available at https://www.liquid.ai/blog/lfm3. Use that source for architecture, training, release and evaluation details.

What models should I compare LFM3-1.7B against?

Common LFM3-1.7B comparisons include LFM3-1.7B vs Nemotron Nano 9B v2, LFM3-1.7B vs DeepSeek R1 Distill Qwen 32B, LFM3-1.7B vs Sarvam-105B. Compare them side by side for benchmark scores, pricing, context window, latency and provider availability.