LiquidAI Releases LFM2.5-2.6B-MLX for Edge Devices
LiquidAI · hf · 2026-08-03
LiquidAI has released a new model, LFM2.5-2.6B-MLX, on Hugging Face. With 2.6 billion parameters and utilizing the MLX architecture, the model is optimized for edge devices like Apple Silicon. It supports text generation and is capable of handling multiple languages, including Chinese, English, and French.
Related event: Liquid AI Launches LFM2.5-2.6B On-Device Agent Model(5 posts)→
More from Models
- Ilya's SSI Expected to Release First Model This Month — socoolandawesome · 2026-08-05
- Qwen3.8-Max Ties Opus 5 in Cybersecurity Benchmark, Lacks Consistency — teortaxesTex · 2026-08-05
- DeepSeek V4 Flash Local Deployment Hits 16k Output Limit — El_90 · 2026-08-05
- Testing 4 Top AI Models on 'Does God Exist?': Huge Differences — Ibz04 · 2026-08-05
- DeepSeek V4 Flash Ranks #21 on Agent Arena, Praised for Open-Source Privacy — Gohab2001 · 2026-08-05
- Grok Integrated into GitHub Copilot: Testing its App Building Capabilities — DanWahlin · 2026-08-05