LF

LFM2.5 Audio 1.5B

LfmGGUF by LiquidAIUpdated 2026-03-30
Download on Hugging Face
Parameters190M
Context125K
Layers8
Architecturelfm2
Smallest quant0.1 GB
Quick answer

LFM2.5 Audio 1.5B needs about 0.8 GB of memory at Q8_0 (a 0.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 9 quants, from 0.1 GB (Q4_0) to 2.3 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 0.5 GB.

LFM2.5 Audio 1.5B – end‑to‑end multimodal speech and text model

LFM2.5 Audio 1.5B is a 1.5 billion‑parameter multimodal model that handles audio input and output. It uses a FastConformer audio encoder and a lightweight audio detokenizer. The model supports real‑time conversational audio generation and non‑conversational ASR/TTS tasks.

Good at

  • Real‑time speech‑to‑speech chat
  • ASR and TTS in a single model
  • Interleaved audio and text generation

Limits

  • No vision support
  • Requires CPU inference via llama.cpp
  • License is other

Best for

  • Audio‑based chatbots
  • Speech recognition and synthesis
  • Multimodal research

Who it’s for. Developers building conversational audio applications or researchers exploring multimodal models. The model is suitable for projects that need both ASR and TTS without separate components.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_00.1 GB 0.7 GB
Fits Get file →
Q8_00.1 GB 0.7 GB
Fits Get file →
Q4_00.1 GB 0.7 GB
Fits Get file →
F160.1 GB 0.8 GB
Fits Get file →
Q8_00.2 GB 0.8 GB
Fits Get file →
F160.4 GB 1.0 GB
Fits Get file →
Q4_00.7 GB 1.3 GB
Fits Get file →
Q8_01.2 GB 1.9 GB
Fits Get file →
F162.3 GB 3.0 GB
Fits Get file →

For 8 GB VRAM, use the Q4_0 quant with file size 0.05 GB, which requires about 0.7 GB memory at 8 k context. If more precision is needed and 16 GB VRAM is available, the Q8_0 quant of 0.08 GB can be used, also requiring 0.7 GB memory. For larger memory budgets, the F16 quant of 2.34 GB needs about 3 GB memory at 8 k context.

What GPU do you need for LFM2.5 Audio 1.5B?

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 F16 (2.3 GB file, about 3.0 GB in use).

Which LFM2.5 Audio 1.5B quant should you choose?

Q8_0 (0.2 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

If memory is tight, the smallest file is Q4_0 at 0.1 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

Architecturelfm2
Parameters190M
Layers8
Trained context128,000 tokens
KV cache (fp16)16 KB per token

Source

Quantized byLiquidAI
FamilyLfm
Licenseother
Downloads (HF)260,908
Last updated2026-03-30

Frequently asked questions about LFM2.5 Audio 1.5B

How much VRAM does LFM2.5 Audio 1.5B need?

About 0.8 GB at Q8_0 with an 8K context window. That is the 0.2 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 LFM2.5 Audio 1.5B on an 8 GB GPU?

Yes, with F16: the 2.3 GB file needs about 3.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of LFM2.5 Audio 1.5B GGUF?

It depends on the quant: Q4_0 is 0.1 GB, Q8_0 is 0.1 GB, Q4_0 is 0.1 GB, F16 is 0.1 GB, Q8_0 is 0.2 GB, F16 is 0.4 GB and 3 more.

What context length does LFM2.5 Audio 1.5B support?

The GGUF header lists a trained context length of 128,000 tokens (125K). The KV cache grows with the context you use: about 0.1 GB at 8K and 0.5 GB at 32K.

Where can I download LFM2.5 Audio 1.5B GGUF?

The files are on Hugging Face in the LiquidAI/LFM2.5-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 LFM2.5 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 LFM2.5 Audio 1.5B on 8 GB VRAM?

Yes, the Q4_0 quant of 0.05 GB uses approximately 0.7 GB memory at 8 k context, fitting within 8 GB VRAM.

Does the model support vision tasks?

No, the model only supports audio and text modalities.

What is the context length of the model?

The trained context tokens are 128000.

Other GGUFs of LFM2.5-Audio-1.5B

Similar models

Browse all →

More from LiquidAI

All by LiquidAI →

More Lfm models

All Lfm →

Other tiny models

All tiny models →