Model Detail
LFM2.5-24B-A2B-MLX-4bit
—LFM2.5-24B-A2B-MLX-4bit is a large language model with 24B parameters released by LiquidAI. The model is registered under the text-generation pipeline tag on Hugging Face, distributed under a other license.
LFM2.5-24B-A2B-MLX-4bit ships with 24B parameters. Total weight footprint is approximately 24.0 GB, which is the relevant figure when planning local-inference VRAM. Distribution is governed by the other license — review the exact terms before commercial deployment.
LFM2.5-24B-A2B-MLX-4bit is best fit for general-purpose chat and instruction-following workloads. Treat this as a starting matrix rather than a benchmark verdict — the right deployment usually depends on the specific evaluation suite that mirrors your workload.
Run fast, private agents on-device with LFM2.5-24B-A2B
Accelerating vision-language models with LFM2.5-VL-DSpark
Up to 3.2x Faster Inference with LFM2.5-DSpark
LFM2.5-Encoders for Fast Long-Context Inference on CPU
Masked Diffusion Language Models are Strong and Steerable Text-Based World Models for Agentic RL
arXiv:2607.16204v1 Announce Type: new Abstract: Recent growth in reinforcement learning (RL) has surfaced a need for diverse, specialized training environments. Hand-curated environments with fixed task and reward difficulties become ineffective signals as model performance improves, and sparse rewa
