LFM2 8B A1B is an open-source language model by LiquidAI. Features: 8b LLM, VRAM: 16.7GB, Context: 125K, License: other.
| LLM Name | LFM2 8B A1B |
| Repository ๐ค | https://huggingface.co/LiquidAI/LFM2-8B-A1B |
| Model Size | 8b |
| Required VRAM | 16.7 GB |
| Updated | 2026-03-27 |
| Maintainer | LiquidAI |
| Model Type | lfm2_moe |
| Model Files | |
| Supported Languages | en ar zh fr de ja ko es |
| Model Architecture | Lfm2MoeForCausalLM |
| License | other |
| Context Length | 128000 |
| Model Max Length | 128000 |
| Transformers Version | 4.57.0.dev0 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | <|pad|> |
| Vocabulary Size | 65536 |
Model |
Likes |
Downloads |
VRAM |
|---|---|---|---|
| LFM2 8B A1B Fp16 | 2 | 25 | 33 GB |
| LFM2 8B A1B 8bit MLX | 7 | 179 | 9 GB |
| LFM2 8B A1B 3bit MLX | 2 | 280 | 4 GB |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| LFM2 8B A1B | 125K / 33.5 GB | 625 | 11 |
| LFM2 8B A1B 3bit MLX | 125K / 4.2 GB | 280 | 2 |
| LFM2 8B A1B 8bit MLX | 125K / 9.4 GB | 179 | 7 |
| LFM2 8B A1B Fp16 | 125K / 33.2 GB | 25 | 2 |
๐ 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! ๐