LFM2 350M 4bit is an open-source language model by mlx-community. Features: 350m LLM, VRAM: 0.2GB, Context: 125K, License: other, Quantized, LLM Explorer Score: 0.19.
| LLM Name | LFM2 350M 4bit |
| Repository 🤗 | https://huggingface.co/mlx-community/LFM2-350M-4bit |
| Base Model(s) | |
| Model Size | 350m |
| Required VRAM | 0.2 GB |
| Updated | 2026-07-23 |
| Maintainer | mlx-community |
| Model Type | lfm2 |
| Model Files | |
| Supported Languages | en ar zh fr de ja ko es |
| Quantization Type | 4bit |
| 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 |
|---|---|---|---|
| LFM2.5 350M MLX 8bit | 125K / 0.4 GB | 839 | 13 |
| LFM2.5 350M MLX 4bit | 125K / 0.2 GB | 405 | 11 |
| CHEETAH 350M Merged FP16 | 125K / 0.7 GB | 13 | 0 |
| LFM2.5 350M MLX 6bit | 125K / 0.3 GB | 108 | 10 |
| LFM2.5 350M MLX 5bit | 125K / 0.3 GB | 98 | 8 |
| ...to Cleanup Lfm25 350M Mlx 5bit | 125K / 0.2 GB | 92 | 2 |
| LFM2 350M 8bit | 125K / 0.4 GB | 423 | 4 |
| LFM2 350M Unsloth Bnb 4bit | 32K / 0.3 GB | 205 | 1 |
| Claude Oss 350M | 125K / 1.4 GB | 841 | 8 |
| LFM2.5 350M | 125K / 0.7 GB | 91807 | 384 |