Ranked by source signals (HN, Lobsters, authority domains, official posts) and recency. Summaries are generated from a stored copy of the article text; every sentence cites a span of that text, and nothing is shown that failed the citation check.
Official3
liquid.ai2026-08-21officialabout the LFM2.5 familyHN 18 pts · 0 comments1,933 words
Liquid AI releases DSpark draft models for LFM2.5-1.2B-Instruct, LFM2.5-2.6B, and LFM2.5-8B-A1B, integrating speculative decoding via llama.cpp and SGLang. The draft models use 5 layers with a block size of 9 and total approximately ~300M parameters, achieving up to 3.18x GPU speedup and up to 2.87x on-device gains for the 2.6B variant. While the 1.2B and 2.6B models see consistent improvements, the 8B-A1B variant only achieves an 18% improvement on edge devices due to current MoE implementation constraints in llama.cpp's Metal backend.written, reviewed, cited
- The 8B-A1B draft model adds 65.5M parameters for its Markov head compared to 33.6M in the 1.2B and 2.6B variants.
- For the 1.2B-Instruct draft, validation loss consistently tracks acceptance rate improvements across all training epochs.
- The 8B-A1B draft model achieves only an 18% improvement on edge devices because verifying k tokens activates more experts and weight traffic.
liquid.ai2026-05-28officialHN 11 pts · 3 comments1,792 words
Liquid AI released LFM2.5-8B-A1B, an edge model designed for fast tool calling on consumer hardware. It features a 128,000 token context window and scaled pretraining to 38T tokens, expanding its vocabulary from 65,536 to 128,000 to improve non-Latin tokenization. The model decodes at 253 tokens/s on an M5 Max and 146 on a Ryzen AI Max+ 395 while staying under 6 GB, reaching 18.5K output tokens per second on a single H100.written, reviewed, cited
- The model doubles its vocabulary to 128K by extending the existing tokenizer in place rather than retraining the model from scratch.
- A targeted preference optimization stage identifies tokens that tend to trigger looping behavior in specific contexts to reduce doom loops.
- The model achieves 18.5K output tokens per second at high concurrency on a single NVIDIA H100 SXM5 GPU.
huggingface.co2026-08-06authorityabout the LFM2.5 familyHN 1 pts · 0 comments1,103 words
Liquid AI releases LFM2.5-Encoder-230M and LFM2.5-Encoder-350M, two new models designed for fast long-context inference on CPU. These encoders support an 8,192-token context and are about 3.7× faster than ModernBERT-base at long context lengths. The models are trained with a masked language objective that masks 30% of tokens during training to achieve strong performance on GLUE, SuperGLUE, and multilingual tasks.written, reviewed, cited
- The 350M variant is the choice when accuracy matters most.
- The 230M variant is the choice for tighter hardware or higher throughput.
- A base encoder provides general-purpose representations rather than direct task outputs.
