LFM2.5 24B A2B Abliterated MLX 4bit is an open-source language model by notfakerv. Features: 24b LLM, VRAM: 13.5GB, Context: 128K, License: other, Quantized, LLM Explorer Score: 0.31.
| LLM Name | LFM2.5 24B A2B Abliterated MLX 4bit |
| Repository 🤗 | https://huggingface.co/notfakerv/LFM2.5-24B-A2B-abliterated-MLX-4bit |
| Base Model(s) | |
| Model Size | 24b |
| Required VRAM | 13.5 GB |
| Updated | 2026-10-20 |
| Maintainer | notfakerv |
| Model Type | lfm2_moe |
| Model Files | |
| Supported Languages | en ar zh fr de ja ko es pt it vi th id hi ru pl |
| Quantization Type | 4bit |
| Model Architecture | Lfm2MoeForCausalLM |
| License | other |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 5.19.0 |
| Tokenizer Class | TokenizersBackend |
| Padding Token | <|pad|> |
| Vocabulary Size | 128000 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| LFM2.5 24B A2B MLX 6bit | 128K / 19.5 GB | 828 | 2 |
| ...5 24B A2B Abliterated 4bit Mlx | 128K / 13.5 GB | 376 | 1 |
| LFM2.5 24B A2B QAD MLX 4bit | 128K / 1.6 GB | 191 | 1 |
| LFM2 24B A2B MLX 8bit | 125K / 25.5 GB | 165 | 18 |
| LFM2 24B A2B MLX 4bit | 125K / 13.4 GB | 183 | 10 |
| LFM2 24B A2B MLX 6bit | 125K / 19.5 GB | 104 | 8 |
| LFM2 24B A2B MLX 5bit | 125K / 16.3 GB | 84 | 6 |
| LFM2.5 24B A2B | 128K / 48.3 GB | 9356 | 424 |
| LFM2.5 24B A2B FP8 | 128K / 24.6 GB | 1691 | 22 |
| LFM2.5 24B A2B Base | 128K / 48.3 GB | 362 | 35 |