Unverified50% confidenceBenchmarkExact time
LFM2.5-24B outperforms Qwen on most benchmarks and is only slightly weaker on Web Arena and Pinch Bench.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/22/2026
First Seen
Valid until: 11/5/2026
Sources
Liquid AI LFM2.5-24B Tested on Mac mini M6: 70 TPS and 128K Context
bilibili安得广厦千万间67810/18/2026
Related Entities
Related Claims
UnverifiedLFM2.5-24B ran successfully with a 128K context window.62% similarUnverifiedLFM2.5-24B-A2B has a total parameter count of 24B, with activated parameters at roughly the 2B level.59% similarUnverifiedLFM2.5-24B-A2B uses a 40-layer architecture: 30 double-gated short convolution blocks + 10 GQA attention layers, 64 experts per MoE block, top-4 routing, a 131,072 token context, and a 128K vocabulary.58% similarUnverifiedFor small-to-medium models that fit within 32 GB of VRAM, the RTX 5090 leads (approximately 45% on Gemma 4 12B and over 75% on GPT-OSS 20B), but the lead on Qwen 3 27B drops from 47% at Q4 to 23% at Q8.58% similarVerifiedQwen3 27B scored 90.3 on LiveCodeBench V6, slightly surpassing Opus 4.6 Max's score of 88.8.58% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1085751API
curl https://kongchang.com/api/v1/knowledge/claims/1085751MCP
get_claim(id=1085751)