LFM3 Audio 2B needs about 3.2 GB of memory at Q4_K_M (a 1.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 5 quants, from 1.0 GB (Q4_0) to 3.5 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.
LFM3 Audio 2B – compact local audio model
LFM3 Audio 2B is a 1.73 B parameter model that accepts text or audio and outputs text, speech, or both. It supports 32K token context and runs locally on laptops and edge devices. The model includes a causal audio encoder and LiquidCodec tokenizer.
Good at
- Real‑time voice chat with tool calls
- Multilingual speech transcription and synthesis
- Audio understanding and reasoning
Limits
- No vision support
- Requires 32K token context
- License is LFM Open License v1.0
Best for
- Local voice assistants
- Audio‑based tool calling
- Multilingual speech synthesis
Who it’s for. Developers building local agents that need audio input and output, or users wanting to run voice‑enabled applications on edge hardware. The model is suitable for applications requiring structured audio responses and tool integration.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_0 | 1.0 GB | 3.2 GB | Fits | Get file → | |
| Q4_K_M | 1.1 GB | 3.2 GB | Fits | Get file → | |
| Q8_0 | 1.8 GB | 4.0 GB | Fits | Get file → | |
| BF16 | 3.5 GB | 5.6 GB | Fits | Get file → | |
| F16 | 3.5 GB | 5.6 GB | Fits | Get file → |
For 8 GB VRAM use Q4_0 or Q4_K_M (≈1.05 GB or 1.1 GB, ~3.2 GB RAM). For 12 GB VRAM use Q8_0 (≈1.85 GB, ~4 GB RAM). For higher precision use BF16 or F16 (≈3.47 GB, ~5.6 GB RAM).
What GPU do you need for LFM3 Audio 2B?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: the best quant that fits is Q8_0 (1.8 GB file, about 4.0 GB in use).
- 6 GB VRAM: the best quant that fits is BF16 (3.5 GB file, about 5.6 GB in use).
Which LFM3 Audio 2B quant should you choose?
Q4_K_M is the usual starting point for LFM3 Audio 2B: it balances file size and quality well. Here it is a 1.1 GB file.
The Q8_0 file is 1.8 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is Q4_0 at 1.0 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about LFM3 Audio 2B
How much VRAM does LFM3 Audio 2B need?
About 3.2 GB at Q4_K_M with an 8K context window. That is the 1.1 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run LFM3 Audio 2B on an 8 GB GPU?
Yes, with BF16: the 3.5 GB file needs about 5.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of LFM3 Audio 2B GGUF?
It depends on the quant: Q4_0 is 1.0 GB, Q4_K_M is 1.1 GB, Q8_0 is 1.8 GB, BF16 is 3.5 GB, F16 is 3.5 GB.
What context length does LFM3 Audio 2B support?
The GGUF header lists a trained context length of 128,000 tokens (125K). The KV cache grows with the context you use: about 1.6 GB at 8K and 6.4 GB at 32K.
Where can I download LFM3 Audio 2B GGUF?
The files are on Hugging Face in the LiquidAI/LFM3-Audio-2B-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does LFM3 Audio 2B use?
Hugging Face lists the license as other. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run LFM3 Audio 2B on 8 GB VRAM?
Yes, using Q4_0 or Q4_K_M quantizations which require about 3.2 GB of RAM at 8K context.
Does the model support vision?
No, LFM3 Audio 2B does not include vision capabilities.
What languages can it synthesize?
It supports Arabic, Danish, German, Greek, British English, American English, Finnish, French, Hebrew, Italian, Japanese, Korean, Dutch, Polish, Portuguese, Spanish, Swedish, Turkish, and Chinese.