LFM2 2.6B Exp is an open-source language model by LiquidAI. Features: 2.6b LLM, VRAM: 5.1GB, Context: 125K, License: other.
Arxiv:2511.23404 Ar Base model:finetune:liquidai/l... Base model:liquidai/lfm2-2.6b-... Conversational De Deploy:azure Edge En Endpoints compatible Es Fr Ja Ko Lfm2 Liquid Region:us Safetensors Sharded Tensorflow Zh
Model Card on HF 🤗: https://huggingface.co/LiquidAI/LFM2-2.6B-Exp
LFM2 2.6B Exp Parameters and Internals
| LLM Name | LFM2 2.6B Exp |
| Repository 🤗 | https://huggingface.co/LiquidAI/LFM2-2.6B-Exp |
| Base Model(s) | |
| Model Size | 2.6b |
| Required VRAM | 5.1 GB |
| Updated | 2026-03-28 |
| Maintainer | LiquidAI |
| Model Type | lfm2 |
| Model Files | |
| Supported Languages | en ar zh fr de ja ko es |
| Model Architecture | Lfm2ForCausalLM |
| License | other |
| Context Length | 128000 |
| Model Max Length | 128000 |
| Transformers Version | 4.57.2 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | <|pad|> |
| Vocabulary Size | 65536 |
Quantized Models of the LFM2 2.6B Exp
Model |
Likes |
Downloads |
VRAM |
|---|---|---|---|
| LFM2 2.6B Exp 8bit | 2 | 495 | 2 GB |
Best Alternatives to LFM2 2.6B Exp
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| LFM2 2.6B Transcript | 125K / 5.1 GB | 269 | 161 |
| LFM2 2.6B | 125K / 5.1 GB | 8996 | 182 |
| LFM2 2.6B Exp 8bit | 125K / 2.7 GB | 495 | 2 |
Note: green Score (e.g. "73.2") means that the model is better than LiquidAI/LFM2-2.6B-Exp .
Rank the LFM2 2.6B Exp Capabilities
🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟
What open-source LLMs or SLMs are you in search of? 52052 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a