Llama · AI Inference · Hugging Face
Both configurations tap a DSpark block size of 9, a batch size of 1, and a temperature of 0
Compiled by KHAO Editorial — aggregated from 1 source. See llms.txt for citation guidance.
★ Tier-1 Source
All three drafter models deliver noticeable throughput improvements on both the large-scale accelerator (H100) and the edge deployment (M4 Max MacBook).
Key facts
- Liquid AI, "LFM2.5-DSpark: Up to 3.2x Faster Inference from H100 to MacBook", Liquid AI Blog, Aug 2026
- Both configurations use a DSpark block size of 9, a batch size of 1, and a temperature of 0
- Across various multi-tool scenarios, DSpark reduces the latency by 57% on average for LFM2.5-2.6B
- For LFM2.5-1.2B-Instruct, they see much more variance in dataset acceptance rates, so speedup varies by as much as 52% depending on the underlying text distribution
Summary
Faster inference: up to 3.18 throughput improvement on a GPU and up to 2.87x on-device. Toward on-device agentic inference: cuts function-calling latency by 57% on average for LFM2.5-2.6B. Day-one support for llama.cpp and SGLang: LFM-compatible DSpark integration is open-sourced upstream. The decode phase in LLM inference is traditionally memory-bound. Over the years, multiple approaches of speculation have been proposed, with the most prominent being EAGLE-3, DFlash, and, most recently, DSpark, which combines three components:.