Model · multimodal model
LFM2.5-VL-DSpark
LFM2.5-VL-DSpark is a multimodal model from Liquid AI, first covered on 24 September 2026. It is available as open weights you can download and run.
Last updated
At a glance
- Made by
- Liquid AI
- Type
- Multimodal model
- Availability
- Open weights
- Licence
- Not stated
- Context window
- Not stated
- First seen
- 24 September 2026
Taken from the coverage, not from our own testing; "not stated" means none of the reports we read gave it. All tracked models →
1 story about LFM2.5-VL-DSpark
-
Liquid AI releases LFM2.5-VL-DSpark for faster vision-language model inference
Liquid AI announced LFM2.5-VL-DSpark, a draft model for its LFM2.5-VL-3B vision-language model. The model uses speculative decoding to speed up inference by up to 3.13x on-device and 2.66x on H100 GPUs, with end-to-end…
1 source primary sourceHugging Face
