LFM2 Audio 1.5B needs about 1.2 GB of memory at F16 (a 0.6 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 4 quants, from 0.4 GB (Q8_0) to 2.3 GB (F16).
LFM2 Audio 1.5B – a 1.5 billion‑parameter end‑to‑end audio model
LFM2 Audio 1.5B is a multimodal speech and text model designed for low‑latency real‑time conversation. It does not require separate ASR or TTS components and supports interleaved generation for conversational chat.
Good at
- Real‑time speech‑to‑speech chat
- ASR and TTS in a single model
- Interleaved audio and text output
Limits
- No LLM capabilities
- Requires --model‑vocoder in TTS examples
- Only English supported
Best for
- Voice‑enabled chatbots
- Real‑time transcription
- Audio‑based virtual assistants
Who it’s for. Developers building conversational agents that need simultaneous audio and text output. Ideal for applications requiring low‑latency speech interaction without separate ASR/TTS pipelines.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 0.4 GB | 0.9 GB | Fits | Get file → | |
| F16 | 0.6 GB | 1.2 GB | Fits | Get file → | |
| Q8_0 | 1.2 GB | 1.9 GB | Fits | Get file → | |
| F16 | 2.3 GB | 3.1 GB | Fits | Get file → |
For 8 GB VRAM use Q8_0 (0.38 GB file, 0.9 GB memory) or F16 (0.6 GB file, 1.2 GB memory). For 12 GB VRAM use Q8_0 (1.25 GB file, 1.9 GB memory) or F16 (2.34 GB file, 3.1 GB memory). Estimates are approximate.
What GPU do you need for LFM2 Audio 1.5B?
These figures add the file size, an fp16 KV cache at an 8K context window 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 F16 (2.3 GB file, about 3.1 GB in use).
Which LFM2 Audio 1.5B quant should you choose?
F16 (0.6 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.
If memory is tight, the smallest file is Q8_0 at 0.4 GB, with the quality trade-offs that come with fewer bits. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about LFM2 Audio 1.5B
How much VRAM does LFM2 Audio 1.5B need?
About 1.2 GB at F16 with an 8K context window. That is the 0.6 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 LFM2 Audio 1.5B on an 8 GB GPU?
Yes, with F16: the 2.3 GB file needs about 3.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of LFM2 Audio 1.5B GGUF?
It depends on the quant: Q8_0 is 0.4 GB, F16 is 0.6 GB, Q8_0 is 1.2 GB, F16 is 2.3 GB.
Where can I download LFM2 Audio 1.5B GGUF?
The files are on Hugging Face in the LiquidAI/LFM2-Audio-1.5B-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 LFM2 Audio 1.5B 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 LFM2 Audio on 8 GB VRAM?
Yes, use the Q8_0 or F16 GGUFs; they require less than 1.2 GB of VRAM at 8k context.
Does the model support multiple languages?
No, it only supports English.
Is there a vision component?
No, the model is audio‑only and cannot process images.