LFM2 350M 8bit is an open-source language model by mlx-community. Features: 350m LLM, VRAM: 0.4GB, Context: 125K, License: other, Quantized, LLM Explorer Score: 0.23.
| LLM Name | LFM2 350M 8bit |
| Repository ๐ค | https://huggingface.co/mlx-community/LFM2-350M-8bit |
| Base Model(s) | |
| Model Size | 350m |
| Required VRAM | 0.4 GB |
| Updated | 2026-03-29 |
| Maintainer | mlx-community |
| Model Type | lfm2 |
| Model Files | |
| Supported Languages | en ar zh fr de ja ko es |
| Quantization Type | 8bit |
| Model Architecture | Lfm2ForCausalLM |
| License | other |
| Context Length | 128000 |
| Model Max Length | 128000 |
| Transformers Version | 4.54.0.dev0 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | <|pad|> |
| Vocabulary Size | 65536 |
| Torch Data Type | bfloat16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| LFM2 350M 4bit | 125K / 0.2 GB | 1168 | 6 |
| LFM2.5 350M Base | 125K / 0.7 GB | 0 | 5 |
| LFM2 350M | 125K / 0.7 GB | 23257 | 188 |
| LFM2 350M ENJP MT | 125K / 0.7 GB | 684 | 52 |
| Luth LFM2 350M | 125K / 0.7 GB | 251 | 15 |
| Kulyk En Uk | 125K / 0.4 GB | 21 | 5 |
| LFM2 350M | 32K / 0.7 GB | 2774 | 4 |
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