On his personal-agent suite, PaulGug scored Liquid AI's LFM3-1.7B level with MiniCPM5 2B and ahead of Qwen 3.5 4B, with 30 of 30 tool calls correct, though it failed a change-of-plan loop. AILogDev reports about 52 tokens a second decoding on an iPhon...
VQV Signal
OPEN SOURCE
WATCH
TECHNICAL
Early LFM3-1.7B tests: perfect tool use, about 52 tokens a second on an iPhone
On his personal-agent suite, PaulGug scored Liquid AI's LFM3-1.7B level with MiniCPM5 2B and ahead of Qwen 3.5 4B, with 30 of 30 tool calls correct, though it failed a change-of-plan loop. AILogDev reports about 52 tokens a second decoding on an iPhon...
On his personal-agent suite, PaulGug scored Liquid AI's LFM3-1.7B level with MiniCPM5 2B and ahead of Qwen 3.5 4B, with 30 of 30 tool calls correct, though it failed a change-of-plan loop. AILogDev reports about 52 tokens a second decoding on an iPhone 17 Pro. Also:...
VQV organizes public signals from inspectable sources. It does not independently verify the underlying report.
Signal Strength 88%
Technical label WATCH
Public Interest 46
Category OPEN SOURCE
Reader Depth TECHNICAL
Signal Strength reflects source quality, relevance, freshness and evidence. Public Interest helps organize discovery; it is not proof of truth.
Public Interest components
Recognizable Entity Score 51
Practical Impact Score 46
Novelty Interest Score 70
Consequence Score 18
Curiosity Score 16
Shareability Score 60
Topics
VQV surfaced this signal because it is recent, relevant to Open Source LLMs, connected to Scobleizer News Pulse (X).
No login, cookies, social SDKs, or automatic posting.