LFM2 8B A1B 8bit MLX is an open-source language model by mlx-community. Features: 8b LLM, VRAM: 9.4GB, Context: 125K, License: other, Quantized.
8-bit 8bit Apple-silicon Base model:liquidai/lfm2-8b-a1... Base model:quantized:liquidai/... Coding Conversational Custom code En Instruct Lfm2 Lfm2 moe Liquidai Long-context Mixture of experts Mlx Moe Quantized Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/mlx-community/LFM2-8B-A1B-8bit-MLX
LFM2 8B A1B 8bit MLX Parameters and Internals
| LLM Name | LFM2 8B A1B 8bit MLX |
| Repository 🤗 | https://huggingface.co/mlx-community/LFM2-8B-A1B-8bit-MLX |
| Base Model(s) | |
| Model Size | 8b |
| Required VRAM | 9.4 GB |
| Updated | 2026-03-27 |
| Maintainer | mlx-community |
| Model Type | lfm2_moe |
| Model Files | |
| Supported Languages | en |
| Quantization Type | 8bit |
| Model Architecture | Lfm2MoeForCausalLM |
| License | other |
| Context Length | 128000 |
| Model Max Length | 128000 |
| Transformers Version | 4.56.1 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | <|pad|> |
| Vocabulary Size | 65536 |
Best Alternatives to LFM2 8B A1B 8bit MLX
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| LFM2 8B A1B 3bit MLX | 125K / 4.2 GB | 280 | 2 |
| LFM2 8B A1B Fp16 | 125K / 33.2 GB | 25 | 2 |
| LFM2 8B A1B | 125K / 16.7 GB | 65601 | 341 |
| LFM2 8B A1B | 125K / 33.5 GB | 625 | 11 |
Rank the LFM2 8B A1B 8bit MLX 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? 51648 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 v20260327b