LFM2.5 230M is an open-source language model by unsloth. Features: 230m LLM, VRAM: 0.5GB, Context: 125K, License: other, LLM Explorer Score: 0.35.
Arxiv:2511.23404 Ar Base model:finetune:liquidai/l... Base model:liquidai/lfm2.5-230... Conversational De Edge En Endpoints compatible Es Fr It Ja Ko Lfm2 Lfm2.5 Liquid Pt Region:us Safetensors Unsloth Zh
Model Card on HF 🤗: https://huggingface.co/unsloth/LFM2.5-230M
LFM2.5 230M Benchmarks
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
LFM2.5 230M Parameters and Internals
| LLM Name | LFM2.5 230M |
| Repository 🤗 | https://huggingface.co/unsloth/LFM2.5-230M |
| Base Model(s) | |
| Model Size | 230m |
| Required VRAM | 0.5 GB |
| Updated | 2026-06-27 |
| Maintainer | unsloth |
| Model Type | lfm2 |
| Model Files | |
| Supported Languages | en ar zh fr de ja ko es pt it |
| Model Architecture | Lfm2ForCausalLM |
| License | other |
| Context Length | 128000 |
| Model Max Length | 128000 |
| Transformers Version | 5.13.0.dev0 |
| Tokenizer Class | TokenizersBackend |
| Padding Token | <|pad|> |
| Vocabulary Size | 65536 |
| Torch Data Type | bfloat16 |
Best Alternatives to LFM2.5 230M
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| LFM2.5 230M | 125K / 0.5 GB | 7334 | 56 |
| LFM2.5 230M Base | 125K / 0.5 GB | 11 | 2 |
| LFM2.5 230M MLX Bf16 | 125K / 0.5 GB | 10 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than unsloth/LFM2.5-230M .
Rank the LFM2.5 230M 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? 54597 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