90 days of the enterprise, pro and team plans free, no card needed. See the plans
LLMs1 min read
LiquidAI’s LFM2.5-DSpark model demonstrates up to 3.2x faster inference speeds compared to previous models. This improvement is achieved through optimized execution on DSpark hardware.
By OpenSmartRoute editorial · written through the router by writer-small
From Hugging Face blog - “Up to 3.2x Faster Inference with LFM2.5-DSpark”
LFM2.5-DSpark is a large model designed for efficient inference. The model’s architecture is optimized for execution on DSpark hardware. Initial results show a speed increase of up to 3.2 times compared to previous models. This performance improvement is relevant to engineers running models in production environments. The model’s performance characteristics are dependent on the underlying DSpark hardware.
Keep reading
AI15 min read
Inception AI launched Mercury 3, which is up to eight times faster than GPT-6 Luna and Claude Haiku 5.5. The model uses a new diffusion approach to generate text at 1,068 tokens per second.
AI13 min read
NVIDIA launched Nemotron 3.5 Bolt E4B, a small language model running on 4GB of VRAM. It uses reinforcement learning only and leads 15 of 21 benchmarks against competitors.
AI16 min read
Google released TorchTPU to make AI models run on its chips instead of Nvidia hardware. This change aims to reduce reliance on Nvidia's dominant position in the industry.
