Q4_0
The conversion repository lists LFM2.5-2.6B-Q4_0.gguf at 1.59 GB; its rounded decimal file size is converted to GiB for planning. This does not include context or runtime memory.
- Bits per weight
- 4.5
- Model size
- 1.48 GiB
Model catalog
LFM2.5 2.6B
Liquid AI's 2.6B text model with a publisher-hosted GGUF conversion. Its listed Q4_0 file is used for weight planning.
Model overview
Available quantizations
Lower-bit quantizations generally use less memory. The compatibility calculator uses these candidates and its transparent approximate memory assumptions; it does not make a performance guarantee.
Compatibility notes
Estimates use the cataloged model-weight size (or a parameter-based estimate), apply weight overhead, and include standard runtime overhead. They do not include context/KV-cache memory. Real requirements vary with runtime, drivers, and other system use. A model page cannot determine compatibility without your hardware profile; use the calculator for that assessment.
Liquid AI LFM2.5 2.6B publisher model card; verified value, last verified 2026-09-29. Liquid AI identifies the 2.6B model, LFM 1.0 license, and 131,072-token context. The publisher also provides a separate GGUF repository; no multimodal auxiliary files are listed for this text model. View source