Llama · AI Inference · Hugging Face
The resulting drafter has approximately 280M parameters and increases the deployed model’s parameter count by 8.9%
Compiled by KHAO Editorial — aggregated from 1 source. See llms.txt for citation guidance.
★ Tier-1 Source
The DSpark draft model for LFM2.5-VL-3B ships with day-one support for llama.cpp, MLX-VLM, and SGLang.
Key facts
- For citations, please use the following reference or BibTeX: Liquid AI, "LFM2.5-VL-DSpark: Accelerating vision-language models on edge and beyond", Liquid AI Blog, Sep 2026
- With llama.cpp on an M3 Ultra, decoding improves by 1.57x to 2.14x and end-to-end by 1.30x to 1.77x
- On H100, the same drafter delivers 20.4x to 2.66x faster decoding, with end-to-end improvements of 1.64x to 2.27x
- Based on ablations across 3, 4, and 5 layers, the draft model is a simplified attention-only drafter with 4 layers and a block size of 9
Summary
Faster inference: decode speedups up to 3.13x on device and 2.66x on an H100, with end-to-end gains up to 2.62x and 2.27x. Small memory cost: the drafter adds 280M parameters, 8.9% on top of the 3B target. Day-one support: LFM-compatible DSpark integrations for llama.cpp, MLX-VLM, and SGLang. The vision drafter uses the same architecture as their text LFM2.5-DSpark drafters: it captures the target model's hidden states at a fixed set of tapped layers and conditions on them to draft a block of k candidate tokens. The team follow the DSpark recipe with a mixture of vision-language SFT data, weighted toward the workloads they expect the model to serve.