Bijan Bowen Tests Liquid LFM2.5 8B

Bijan Bowen21m 10s
Bijan Bowen beside the words Liquid AI 8B on black.
0 comments · 0 votesOpen discussionClose discussion
Sign in to join the discussion

    Bijan Bowen reviews Liquid AI’s LFM2.5 8B A1B and tests an 8-bit version on a laptopA local model runs on computing infrastructure controlled directly by the user rather than only through a remote model service.. He tries coding and role play, noting both useful results and limitations in a browser interface.

    A simulated IT helpdesk task shows the model chaining tool calls, though Bowen finds that it escalates before completing an available troubleshooting step. He also tests factual knowledge and a simple Python gameEvaluation is the systematic assessment of a system's behaviour or results against explicit criteria.; the results are informal observations rather than a comprehensive benchmark.

    Original YouTube thumbnailWatch on YouTube

    Video topic coverage

    • Agents & workflows70
    • Coding & tools75
    • Models & learning100
    • Infrastructure & compute75
    • Research & evaluation85
    • Safety & security0
    • Business & productivity40
    • Creative & media0
    • Robotics & perception0
    • Society & policy0

    Share this video

    Bijan Bowen beside the words Liquid AI 8B on black. With WWW.ARTIFICIAL-INTELLIGENCE.VIDEO, 18 June 2026 and duration 21m 10s.

    Bijan Bowen tests a small mixture-of-experts model locally, including its ability to call tools and write code.