### LFM2.5-VL-DSpark: Accelerating vision-language models on edge and beyond

- [LFM2.5-VL-DSpark: Accelerating vision-language models on edge and beyond](/content/blog/lfm2-5-vl-dspark/index.html) - 09.24.2026
- [LFM2.5-DSpark: Up to 3.2x Faster Inference from H100 to MacBook](/content/blog/lfm2.5-dspark/index.html) - 08.20.2026
- [LFM2.5 Q4_0: Quantization-Aware Distillation for Edge Deployment](/content/blog/qad/index.html) - 08.19.2026
- [LFM2.5-VL-3B: A Better and Faster Vision-Language Model for the Edge](/content/blog/lfm2-5-vl-3b/index.html) - 08.12.2026
- [LFM2.5-2.6B: Deploy Agents Everywhere](/content/blog/lfm2-5-2-6b/index.html) - 08.04.2026
- [LFM2.5-Encoders: Fast at Long Context, Even on CPU](/content/blog/lfm2-5-encoders/index.html) - 07.28.2026
- [LFM2.5-230M: Built to Run Anywhere](/content/blog/lfm2-5-230m/index.html) - 06.25.2026
- [LFM2.5 Retrievers: Bi-directional LFMs for Fast Multilingual Search](/content/blog/lfm2-5-retrievers/index.html) - 06.18.2026
- [LFM2.5-8B-A1B: An Even Better On-Device Mixture of Experts](/content/blog/lfm2-5-8b-a1b/index.html) - 05.28.2026
- [LFM2.5-VL-450M: Structured Visual Intelligence, Edge to Cloud](/content/blog/lfm2-5-vl-450m/index.html) - 04.08.2026
- [LFM2.5-350M: No Size Left Behind](/content/blog/lfm2-5-350m-no-size-left-behind/index.html) - 03.31.2026
- [No Cloud, No Waiting: Tool-Calling Agents on Consumer Hardware with LFM2-24B-A2B](/content/blog/no-cloud-tool-calling-agents-consumer-hardware-lfm2-24b-a2b/index.html) - 03.05.2026
- [LFM2-24B-A2B: Scaling Up the LFM2 Architecture](/content/blog/lfm2-24b-a2b/index.html) - 02.24.2026
- [LFM2.5-1.2B-Thinking: On-Device Reasoning Under 1GB](/content/blog/lfm2-5-1-2b-thinking-on-device-reasoning-under-1gb/index.html) - 01.20.2026
- [The Future of Meeting Summarization: Local, Fast, Private, and Fully Secure](/content/blog/the-future-of-meeting-summarization-local-fast-private-and-fully-secure/index.html) - 01.07.2026
- [Introducing LFM2.5: The Next Generation of On-Device AI](/content/blog/introducing-lfm2-5-the-next-generation-of-on-device-ai/index.html) - 01.05.2026
- [LFM2-ColBERT-350M: One Model to Embed Them All](/content/blog/lfm2-colbert-350m-one-model-to-embed-them-all/index.html) - 10.28.2025
- [How Liquid AI Uses ExecuTorch to Power Efficient, Flexible On-Device Intelligence](/content/blog/how-liquid-ai-uses-executorch-to-power-efficient-flexible-on-device-intelligence/index.html) - 10.22.2025
- [LFM2-VL-3B: A New Efficient Vision-Language for the Edge](/content/blog/lfm2-vl-3b-a-new-efficient-vision-language-for-the-edge/index.html) - 10.22.2025
- [LFM2-8B-A1B: An Efficient On-device Mixture-of-Experts](/content/blog/lfm2-8b-a1b-an-efficient-on-device-mixture-of-experts/index.html) - 10.07.2025
- [LFM2-Audio: An End-to-End Audio Foundation Model](/content/blog/lfm2-audio-an-end-to-end-audio-foundation-model/index.html) - 10.01.2025
- [Introducing Liquid Nanos — frontier‑grade performance on everyday devices](/content/blog/introducing-liquid-nanos-frontier-grade-performance-on-everyday-devices/index.html) - 09.25.2025
- [Introducing LFM2-2.6B: Redefining Efficiency in Language Models](/content/blog/introducing-lfm2-2-6b-redefining-efficiency-in-language-models/index.html) - 09.23.2025
- [From Cloud to Keyboard: LEAP Expands to Laptops with Cutting-Edge AMD Ryzen™ Power](/content/blog/liquids-edge-ai-platform-leap-expands-support-to-laptops-with-best-in-class-performance-on-amd-ryzen-tm-and-ryzen-ai-tm-processors/index.html) - 08.18.2025
- [LFM2-VL: Efficient Vision-Language Models](/content/blog/lfm2-vl-efficient-vision-language-models/index.html) - 08.12.2025
- [Liquid <> .txt Collaboration](/content/blog/liquid-txt-collaboration/index.html) - 07.24.2025
- [Liquid AI Launches LEAP and Liquid Apollo: The Easiest Way to Build with On-Device AI](/content/blog/liquid-ai-launches-leap-and-apollo-bringing-edge-ai-to-every-developer/index.html) - 07.15.2025
- [Introducing LFM2: The Fastest On-Device Foundation Models on the Market](/content/blog/liquid-foundation-models-v2-our-second-series-of-generative-ai-models/index.html) - 07.10.2025
- [LFM-1B-Math: Can Small Models Be Concise Reasoners?](/content/blog/lfm-1b-math-can-small-models-be-concise-reasoners/index.html) - 06.24.2025
- [Introducing LFM-7B: Setting New Standards for Efficient Language Models](/content/blog/introducing-lfm-7b-setting-new-standards-for-efficient-language-models/index.html) - 01.20.2025
- [Liquid Foundation Models: Our First Series of Generative AI Models](/content/blog/liquid-foundation-models-our-first-series-of-generative-ai-models/index.html) - 09.30.2024