LF

lfm2 audio 1.5b

LfmGGUF by cstrUpdated 2026-08-02
Download on Hugging Face
Parameters79M
Context—
Layers—
Architecturelfm2-audio-detok
Smallest quant0.2 GB
Quick answer

lfm2 audio 1.5b needs about 2.4 GB of memory at Q5_K (a 1.7 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 4 quants, from 0.2 GB (F16) to 3.1 GB (F16).

1.5B‑parameter end‑to‑end audio model for ASR, TTS and speech‑to‑speech

LFM2‑Audio‑1.5B is a 1.5‑billion‑parameter multimodal speech model. It supports English ASR, TTS, and real‑time speech‑to‑speech in a single model. The model is available as GGUF files for CPU inference via llama.cpp.

Good at

  • Real‑time speech‑to‑speech
  • English ASR
  • Text‑to‑speech

Limits

  • No vision support
  • Requires English only
  • License allows commercial use only for entities under $10M revenue

Best for

  • Embedded speech assistants
  • Low‑latency voice chatbots
  • Audio transcription tools

Who it’s for. Developers building conversational voice interfaces who need a single model for ASR, TTS, and speech‑to‑speech. The model is suitable for CPU‑only deployments using llama.cpp.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F160.2 GB 0.7 GB
Fits Get file →
Q5_K1.7 GB 2.4 GB
Fits Get file →
Q8_02.1 GB 2.8 GB
Fits Get file →
F163.1 GB 4.0 GB
Fits Get file →

For 8 GB VRAM, use the Q5_K quant (1.67 GB, ~2.4 GB memory at 8 k context). If you have 16 GB VRAM, the Q8_0 quant (2.09 GB, ~2.8 GB memory) offers higher quality. The smallest F16 quant (0.16 GB, ~0.7 GB memory) is best for very limited memory budgets.

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 (3.1 GB file, about 4.0 GB in use).

Which lfm2 audio 1.5b quant should you choose?

Q5_K (1.7 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

If memory is tight, the smallest file is F16 at 0.2 GB, with the quality trade-offs that come with fewer bits. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturelfm2-audio-detok
Parameters79M

Source

Quantized bycstr
FamilyLfm
Licenseother
Downloads (HF)1,185
Last updated2026-08-02

Frequently asked questions about lfm2 audio 1.5b

How much VRAM does lfm2 audio 1.5b need?

About 2.4 GB at Q5_K with an 8K context window. That is the 1.7 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 3.1 GB file needs about 4.0 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: F16 is 0.2 GB, Q5_K is 1.7 GB, Q8_0 is 2.1 GB, F16 is 3.1 GB.

Where can I download lfm2 audio 1.5b GGUF?

The files are on Hugging Face in the cstr/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‑1.5B on 8 GB VRAM?

Yes, the Q5_K quant uses 1.67 GB file size and requires about 2.4 GB VRAM at 8 k context.

Does this model support languages other than English?

No, the current GGUF variant is English only.

What license does the model use?

LFM Open License v1.0, commercial use allowed for entities with annual revenue under $10M USD.

Other GGUFs of LFM2.5-Audio-1.5B

Similar models

Browse all →

More from cstr

All by cstr →

More Lfm models

All Lfm →

Other tiny models

All tiny models →