You need to agree to share your Hugging Face information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Terms of access and use

By requesting access to, downloading or using this model, including its weights, code and anything it generates, you agree to these terms.

  1. Your responsibility. You alone are responsible for how you use this model and for everything it produces for you. You accept full liability for that use and for those outputs, including any decision you make, action you take or content you share because of them.
  2. No warranty. The model is provided "as is" and "as available", without warranties of any kind, express or implied, including merchantability, fitness for a particular purpose, accuracy, title and non-infringement.
  3. No liability. To the fullest extent the law allows, the authors and publishers of this repository are not liable for any damages, claims, losses or costs, whether direct, indirect, incidental, special, consequential or punitive, that arise from or relate to your access to or use of the model or its outputs, however caused.
  4. Indemnity. You will indemnify, defend and hold harmless the authors and publishers against any claim, damage, loss, liability or cost, including reasonable legal fees, that arises from your use of the model or its outputs or from your breach of these terms.
  5. Laws and licences. You will follow every law that applies to you, the licence of this repository and the licence of every model or dataset it is built on. These terms add to those licences and do not take away any right they grant you.
  6. Agreement. Accessing or downloading this repository means you agree to these terms. If you do not agree, do not access, download or use it. If any part of these terms cannot be enforced, the rest still applies.

Log in or Sign Up to review the conditions and access this model content.

LFM3-Audio-2B, MLX for Apple Silicon

This repo holds the MLX build of LFM3-Audio-2B by Liquid AI. Its linear layers are 8-bit (round to nearest, groups of 64), made from the original weights. The weights take 2.3 GB.

Which file do I use?

Your hardware Build Repo
Apple Silicon Mac (this one) 8-bit MLX weights made from the original balllvin/LFM3-Audio-2B-MLX
Any, full precision The original weights LiquidAI/LFM3-Audio-2B

Set it up with a coding agent

Paste this into a coding agent such as Claude Code or OpenCode. Edit the first line first.

Use it in: [Insert application you will use it in, for example OpenCode]

Set up LFM3-Audio-2B (MLX build) on this computer. Do every step yourself.
1. Check the tools: Python 3.12, uv or pip, git, the Hugging Face CLI (`hf`). If the HF CLI is missing, tell me and show me how to install it; do not install it yourself.
2. Check the hardware. This build needs an Apple Silicon Mac with at least 8 GB of memory. Anything else: tell me it will not run here, and suggest the original model's own runtimes.
3. Ask me to open https://huggingface.co/balllvin/LFM3-Audio-2B-MLX and accept the terms at the top of the page, then run `hf auth login` (or set HF_TOKEN). Download the repo with the HF CLI and check every file against the repo's file list.
4. Install the runtime in a fresh virtual environment: `uv pip install mlx==0.32.4 mlx-vlm==0.7.12`.
5. Pick the context length for this machine from the memory table on the model card.
6. Ask one question with no tools, check the answer makes sense. Report the speed. If anything fails, fix it and try again.
7. Start the OpenAI-compatible server and connect it to the application on the first line, with that application's output limit for this model raised to the context length (no application: show one curl call).
8. Report what you set up, the server address if there is one, and one command to start it again.

Quick check

We ran it with mlx-vlm 0.7.12 on an M5 Pro Mac with 64 GB (other jobs running, greedy decoding) and asked: "What is 17 times 23? Answer in one short sentence." It answered:

Reasoning: We need to answer: "What is 17 times 23? Answer in one short sentence." Compute 17 * 23. 17 * 20 = 340 17 * 3 = 51 340 + 51 = 391. So answer: 391. One short sentence: "17 times 23 equals 391." Check: "17 times 23 is 391." That's one short sentence.

Answer: 17 times 23 equals 391.

Prompt 23 tokens at 216.9 tokens/s, 102 new tokens at 105.0 tokens/s, peak memory 2.42 GB. The Mac was shared, so these speeds are a floor, not a benchmark.

Memory

GB means 10^9 bytes; K means 1,024 tokens. The weights take 2.3 GB (2,334,813,259 bytes, measured on the files in this repo).

Run it

Before the first download, accept the terms at the top of this page, then log in with the Hugging Face CLI (hf auth login) or set HF_TOKEN to a read token.

The model runs with mlx-vlm 0.7.12. Use the sampling settings from the original model's card.

uv venv --python 3.12 && source .venv/bin/activate
uv pip install mlx==0.32.4 mlx-vlm==0.7.12
python -m mlx_vlm.generate --model balllvin/LFM3-Audio-2B-MLX --max-tokens 2048 --prompt "What is 17 times 23?"
python -m mlx_vlm.server --model balllvin/LFM3-Audio-2B-MLX --port 8080

The server speaks the OpenAI chat API at http://127.0.0.1:8080/v1.

How it was made

  1. Source: LiquidAI/LFM3-Audio-2B (revision 2d6c1f99), the original weights.
  2. mlx-vlm 0.7.12 quantized every linear layer to 8-bit (affine, groups of 64, round to nearest); layers the model code keeps in full precision stay bf16.
  3. MLX 0.32.4 on an M5 Pro Mac. No training, no change to what the model learned.

Credits

Licence

The weights are under the LFM Open License v1.0, the licence of the original model; this repo carries its licence files unchanged and NOTICE.md with the origin of every file and what we changed. This is an independent community build, unaffiliated with Liquid AI.

Terms of use

Access to this repository requires agreeing to the terms in the access form on this page. In short: you alone are responsible and liable for your use of this model and for everything that comes from it, it is provided as is with no warranty, and its authors are not liable for any result of that use. Full text: TERMS.md.

To download after you agree, log in with the Hugging Face CLI (hf auth login) or set HF_TOKEN.

Downloads last month
2
Safetensors
Model size
2B params
Tensor type
BF16
·
U32
·
MLX
Hardware compatibility
Log In to add your hardware

8-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for balllvin/LFM3-Audio-2B-MLX

Quantized
(18)
this model