Storia in 3 fonti

Liquid AI Ships LFM2.5-230M with llama.cpp, MLX, vLLM, SGLang, and ONNX Support for On-Device Inference

Liquid AI's LFM2.5-230M is a 230M-parameter open-weight on-device model for fast tool use and large-scale data extraction.

Raccontata da

venturebeat.com

cryptobriefing.com

marktechpost.com

Confronto fonti

3 prospettive sulla stessa storia

AI · summaries

marktechpost.comStai leggendo4 g fa

Liquid AI Ships LFM2.5-230M with llama.cpp, MLX, vLLM, SGLang, and ONNX Support for On-Device Inference

Liquid AI shipped LFM2.5-230M (230M params, 293 MB), tuned for on-device agentic inference, beating larger models on instruction following and data extraction. Local edge processing eliminates cloud API costs, enabling enterprises to deploy automation pipelines on phones, robots, and commodity hardware.

originale

venturebeat.com6 g fa

Liquid AI's smallest model yet LFM2.5-230M beats models 4X its size at data extraction, can run 'anywhere'

LFM2.5-230M proves that while 3-billion-parameter models like VibeThinker are solving advanced calculus, a 230-million-parameter model is the superior, highly optimized choice for executing structured tool calls and…

Leggi questa versione → originale

cryptobriefing.com6 g fa

Liquid AI releases LFM2.5-230M model, outperforming larger competitors in data extraction

Liquid AI's new 230-million-parameter LFM2.5-230M model outperforms Alibaba and Google models four times its size on data extraction benchmarks.

Leggi questa versione → originale

Liquid AI Ships LFM2.5-230M with llama.cpp, MLX, vLLM, SGLang, and ONNX Support for On-Device Inference

Confronto fonti

Liquid AI Ships LFM2.5-230M with llama.cpp, MLX, vLLM, SGLang, and ONNX Support for On-Device Inference

Liquid AI's smallest model yet LFM2.5-230M beats models 4X its size at data extraction, can run 'anywhere'

Liquid AI releases LFM2.5-230M model, outperforming larger competitors in data extraction

Timeline cronologica

Liquid AI's smallest model yet LFM2.5-230M beats models 4X its size at data extraction, can run 'anywhere'

Liquid AI releases LFM2.5-230M model, outperforming larger competitors in data extraction

Liquid AI Ships LFM2.5-230M with llama.cpp, MLX, vLLM, SGLang, and ONNX Support for On-Device Inference

Liquid AI Ships LFM2.5-230M with llama.cpp, MLX, vLLM, SGLang, and ONNX Support for On-Device Inference

Confronto fonti

Liquid AI Ships LFM2.5-230M with llama.cpp, MLX, vLLM, SGLang, and ONNX Support for On-Device Inference

Liquid AI's smallest model yet LFM2.5-230M beats models 4X its size at data extraction, can run 'anywhere'

Liquid AI releases LFM2.5-230M model, outperforming larger competitors in data extraction

Timeline cronologica

Liquid AI's smallest model yet LFM2.5-230M beats models 4X its size at data extraction, can run 'anywhere'

Liquid AI releases LFM2.5-230M model, outperforming larger competitors in data extraction

Liquid AI Ships LFM2.5-230M with llama.cpp, MLX, vLLM, SGLang, and ONNX Support for On-Device Inference