LiquidAI's LFM2.5-DSpark Gets 3.2x Speedup with Speculative Decoding, GGUF Released

LiquidAI released the GGUF version of its 1.2B LFM2.5-DSpark model, which achieves up to 3.2x faster inference with speculative decoding.

2026-08-19 ~ 2026-08-21 · 2 related posts

• LiquidAI Releases GGUF Version of LFM2.5 1.2B with Speculative Decoding — LiquidAI · 2026-08-19
• LFM2.5-DSpark offers up to 3.2x faster inference — pmttyji · 2026-08-21