| --- |
| library_name: mlx |
| license: other |
| license_name: lfm1.0 |
| license_link: LICENSE |
| language: |
| - ar |
| - zh |
| - en |
| - fr |
| - de |
| - hi |
| - id |
| - it |
| - ja |
| - ko |
| - pl |
| - pt |
| - ru |
| - es |
| - th |
| - vi |
| pipeline_tag: text-generation |
| tags: |
| - liquid |
| - lfm2.5 |
| - edge |
| - mlx |
| base_model: LiquidAI/LFM2.5-2.6B |
| --- |
| |
| <div align="center"> |
| <img |
| src="https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/2b08LKpev0DNEk6DlnWkY.png" |
| alt="Liquid AI" |
| style="width: 100%; max-width: 100%; height: auto; display: inline-block; margin-bottom: 0.5em; margin-top: 0.5em;" |
| /> |
| <div style="display: flex; justify-content: center; gap: 0.5em; margin-bottom: 1em;"> |
| <a href="https://playground.liquid.ai/"><strong>Try LFM</strong></a> • |
| <a href="https://docs.liquid.ai/lfm/getting-started/welcome"><strong>Docs</strong></a> • |
| <a href="https://leap.liquid.ai/"><strong>LEAP</strong></a> • |
| <a href="https://discord.com/invite/liquid-ai"><strong>Discord</strong></a> |
| </div> |
| </div> |
| |
| # LFM2.5-2.6B-MLX |
|
|
| LFM2.5 is a new family of hybrid models designed for **on-device deployment**. It builds on the LFM2 architecture with extended pre-training and reinforcement learning. |
|
|
| Find more details in the original model card: https://huggingface.co/LiquidAI/LFM2.5-2.6B |
|
|
| ## Precisions |
|
|
| | Folder | Precision | Group Size | Size | |
| |--------|-----------|------------|------| |
| | [`bf16/`](https://huggingface.co/LiquidAI/LFM2.5-2.6B-MLX/tree/main/bf16) | bf16 | - | 5.02 GB | |
| | [`8bit/`](https://huggingface.co/LiquidAI/LFM2.5-2.6B-MLX/tree/main/8bit) | 8-bit | 64 | 2.67 GB | |
| | [`6bit/`](https://huggingface.co/LiquidAI/LFM2.5-2.6B-MLX/tree/main/6bit) | 6-bit | 64 | 2.04 GB | |
| | [`5bit/`](https://huggingface.co/LiquidAI/LFM2.5-2.6B-MLX/tree/main/5bit) | 5-bit | 64 | 1.76 GB | |
| | [`4bit/`](https://huggingface.co/LiquidAI/LFM2.5-2.6B-MLX/tree/main/4bit) | 4-bit | 64 | 1.47 GB | |
| | [`mxfp8/`](https://huggingface.co/LiquidAI/LFM2.5-2.6B-MLX/tree/main/mxfp8) | MXFP8 | 32 | 2.59 GB | |
| | [`mxfp4/`](https://huggingface.co/LiquidAI/LFM2.5-2.6B-MLX/tree/main/mxfp4) | MXFP4 | 32 | 1.46 GB | |
| | [`nvfp4/`](https://huggingface.co/LiquidAI/LFM2.5-2.6B-MLX/tree/main/nvfp4) | NVFP4 | 16 | 1.53 GB | |
|
|
| ## Use with mlx |
|
|
| `mlx_lm.load` does not resolve subfolders of a HuggingFace repo directly (ml-explore/mlx-lm#403), so download the precision you want first: |
|
|
| ```bash |
| pip install mlx-lm |
| ``` |
|
|
| ```python |
| from huggingface_hub import snapshot_download |
| from mlx_lm import load, generate |
| from mlx_lm.sample_utils import make_sampler |
| |
| path = snapshot_download("LiquidAI/LFM2.5-2.6B-MLX", allow_patterns=["4bit/*"]) |
| model, tokenizer = load(f"{path}/4bit") |
| |
| response = generate( |
| model, |
| tokenizer, |
| prompt="The capital of France is", |
| max_tokens=100, |
| sampler=make_sampler(temp=0.7), |
| verbose=True, |
| ) |
| ``` |
|
|
