LLMfamily
LFM2.5
Liquid AI's LFM2.5 hybrid conv-attention models for CPU and edge; GGUF, ONNX and MLX variants.
Levelfamily
ClassLLM
Parametersnot in the notes
Contextnot in the notes
ReleasedAug 2026
Opennessopen weights restricted
Runs onnot in the notes
Statusactive
Benchmark Results
Where this comes from
Every score names who ran it: vendor-reported, maintainer-run or independent. A rank is shown with the population it was ranked in (gap rule 3).
Lineage
LFM2.5-Encoder 230M belongs to this familyembeddingOct 2026230MLFM2.5-Encoder 350M belongs to this familyembeddingOct 2026350MLFM2.5-2.6B belongs to this familyedge LLMAug 20262.6BLFM2.5-230M belongs to this familyedge LLMAug 2026230MLFM2.5-350M belongs to this familyedge LLMAug 2026350MLFM2.5-8B-A1B belongs to this familyedge LLMAug 20268.3BLFM2.5-VL-3B belongs to this familymultimodal LLMAug 20263BWhere this comes from
Parent and child relations from model cards, Hugging Face base_model fields and the genealogy tables of the research notes. Confidence and evidence are the notes' own.
R&D Topics
Identity
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.
Architecture and Size
- Architecture
- hybrid Double-gated convolution + GQA
- Total parameters
- – sources
- Active parameters
- –
- Checkpoint parameters
- –
- Context length
- not in the notes
- Input
- text
- Output
- text
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).
Openness and Access
- Openness
- open weights restricted
- Licence
- LFM Open License 1.0 (lfm1.0) sources
- Access routes
- open weights download
Where this comes from
The licence file governs over registry tags and aggregator labels.
Deployment
- Runs on
- not in the notes
- Footprint
- not in the notes
- Runtimes
- not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.
Indonesia
- Indonesian support
- not stated
- Regional languages
- not in the notes
- Jakarta hosting
- unknown
- Languages
- not in the notes
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.
Industry Use Cases
No industry use case links this model.
Links
DeveloperLiquid AIstartup, USA
Liquid AIstartup, USAModelLFM2.5Liquid AI, LLM
LFM2.5Liquid AI, LLMUse CasesIndustrial Copilots and Maintenance AssistantsIndustrialIndonesian and Regional-Language LLMsPublic SectorTelecom Domain LLMs and BenchmarksTelecomUse cases of models in the same R&D topic; none is recorded for this model itself.
Who Runs It
PT Pertamina Geothermal EnergyIn production, 14 Jul 2026
Siemens Erlangen electronics factoryPlanned, 6 Jan 2026
ADNOC OffshoreIn production, 9 Sep 2025
Aker BPIn production, 9 Sep 2025+10 moreDeployments of these use cases; none names this model.
PT Pertamina Geothermal EnergyIn production, 14 Jul 2026Siemens Erlangen electronics factoryPlanned, 6 Jan 2026ADNOC OffshoreIn production, 9 Sep 2025Aker BPIn production, 9 Sep 2025+10 moreDeployments of these use cases; none names this model.Models 7
Organisations 1
Sources
- huggingface.co/LiquidAI https://huggingface.co/LiquidAI
- huggingface.co/LiquidAI/LFM2.5-8B-A1B https://huggingface.co/LiquidAI/LFM2.5-8B-A1B
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "LFM2.5", https://aurion.semai.id/models/liquid-ai-lfm2-5/, records of October 2026.