● DAMMNEWS STORY INTEL • ROUTE A LOCAL/FREE • NO PAID AI API ●
DAMMNEWS®
Independent aggregation • v2.4.14 • 2026-08-06

LIQUID AI RELEASES LFM2.5-2.6B: AN ON-DEVICE AGENTIC MODEL WITH 128K CONTEXT, TOOL CALLING, AND OPEN WEIGHTS

1 min read • 2 hrs ago • MarkTechPost • [src]
SOURCE SPECTRUM: MarkTechPost Unrated
LEFTCENTRERIGHTUNRATED
Third-party classification: Not ratedmethod and full source list. Bias is not a truth score.
REPORT A PROBLEM WITH THIS SOURCE
Reports are reviewed by the DAMMNEWS administrator. Please do not include personal or sensitive information.

SOURCE AGREEMENT & OPEN QUESTIONS

WHAT SOURCES AGREE ON
One linked publisher is currently carrying this report in the live cache.

WHAT REMAINS UNCLEAR
RSS excerpts are short and may omit qualifications, timing or attribution. Read the original reports before treating a detail as settled.

WHERE REPORTING MAY DIFFER
Independent comparison coverage has not yet been identified in the current live cache.

SOURCE COMPARISON

SourceLatest linked headlineAge
MarkTechPostLIQUID AI RELEASES LFM2.5-2.6B: AN ON-DEVICE AGENTIC MODEL WITH 128K CONTEXT, TOOL CALLING, AND OPEN WEIGHTS2 hrs ago

WHAT HAPPENED

Liquid AI released LFM2.5-2.6B, an agentic model that plans, calls tools, and completes multi-step tasks entirely on-device. The 2.69B parameter model pairs 22 double-gated short convolution blocks with 8 GQA blocks across 30 layers, handles 131,072 tokens of context, and decodes at 220 tokens/s on an M5 Max in under 2.5 GB.

MarkTechPost reports that liquid AI released LFM2.5-2.6B, an agentic model that plans, calls tools, and completes multi-step tasks entirely on-device.

The report adds: The 2.69B parameter model pairs 22 double-gated short convolution blocks with 8 GQA blocks across 30 layers, handles 131,072 tokens of context, and decodes at 220 tokens/s on an M5 Max in under 2.5 GB.

Open weights ship in GGUF, MLX, and ONNX.

This report is covered across the current DAMMNEWS feeds. Technology stories often mix a product announcement with claims about availability, performance or impact. Those parts should be checked separately.

This is a developing report. DAMMNEWS will surface related coverage as closely matched reporting enters the live cache.

DAMMNEWS RSS BRIEFING — generated locally from the available MarkTechPost headline and RSS excerpt. It is not a summary of the full source article.

ADVERTISEMENT

RELATED DAMMNEWS COVERAGE

Built locally from the available RSS excerpts for this story and closely related DAMMNEWS coverage. Statements are attributed to their feed source; no paid AI API was used. Short excerpts can omit important context, so the original source remains essential.
READ FULL AT SOURCE →
ADVERTISEMENT
TEXT MODE PRINT SHARE: X Facebook Email ← Front page
ADVERTISEMENT
DAMMNEWS® 2026 • Local rules-based story intelligence • Original source remains one click away
RSSSource SpectrumAboutPrivacyContactTerms