Unverified50% confidenceBenchmarkExact time
Running LFM2.5-24B uses about 28GB of memory, with the model fully loaded and running OpenClaw background tasks.
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
UnverifiedSwitching the model to LFM2.5-2.6B (run via the Mirai AI server), on the same OpenClaw task, reduced memory usage to 17GB with a generation speed of about 54.2 tokens/second, and the task was not completed in time.73% similarUnverifiedWhen the model loads, it first allocates a full-precision shell of approximately 1.29 GB and then reads in 643 MB of full weights, with peak memory potentially reaching approximately 3,400 MB.68% similarUnverifiedOpenTPU 运行 LFM 2.5 230M 模型可达到约 59 tokens/秒，在 4-bit 量化下提升到 85.8 tokens/秒68% similarUnverifiedIn the replaced model, the tied embedding/lm_head matrix remains bf16, so each token actually reads about 1.263 GB of weights (plus about 0.06 GB of KV cache); calculated by actual bytes moved, 25.5 tok/s corresponds to about 34 GB/s, roughly 10% of measured bandwidth.67% similarUnverifiedMeta's LLaMA 2 70B model still requires approximately 35 GB of VRAM to fully load even with 4-bit quantization.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1085752API
curl https://kongchang.com/api/v1/knowledge/claims/1085752MCP
get_claim(id=1085752)