LFM2.5-Audio-1.5B needs about 2.3 GB of memory at Q4_K_M (a 0.7 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 22 quants, from 0.0 GB to 2.3 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
LFM2.5‑Audio‑1.5B – 1.5 B parameter audio‑text model
LFM2.5‑Audio‑1.5B is a 1.5 B parameter multimodal speech and text model. It runs with llama.cpp GGUFs and supports real‑time speech‑to‑speech and non‑conversational ASR/TTS. The model is optimized for low latency and CPU inference.
Good at
- Real‑time speech‑to‑speech chat
- Low‑latency ASR and TTS
- Multimodal audio‑text interaction
Limits
- No vision support
- Requires English language only
- Large memory for high context
Best for
- Voice‑enabled chatbots
- Speech transcription services
- Audio‑based RAG systems
Who it’s for. Developers building voice‑first applications on edge devices or CPUs. The model is suitable for real‑time conversational agents and audio transcription pipelines.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 1.6 GB | Fits | Get file → | |
| IQ3_M | 0.6 GB | 2.1 GB | Fits | Get file → | |
| IQ3_S | 0.6 GB | 2.1 GB | Fits | Get file → | |
| Q3_K_S | 0.6 GB | 2.2 GB | Fits | Get file → | |
| Q3_K_M | 0.6 GB | 2.2 GB | Fits | Get file → | |
| Q4_0 | 0.7 GB | 2.2 GB | Fits | Get file → | |
| IQ4_XS | 0.7 GB | 2.2 GB | Fits | Get file → | |
| Q3_K_L | 0.7 GB | 2.2 GB | Fits | Get file → | |
| IQ4_NL | 0.7 GB | 2.3 GB | Fits | Get file → | |
| Q4_K_S | 0.7 GB | 2.3 GB | Fits | Get file → | |
| Q4_1 | 0.7 GB | 2.3 GB | Fits | Get file → | |
| Q4_K_M | 0.7 GB | 2.3 GB | Fits | Get file → | |
| Q4_K_L | 0.8 GB | 2.3 GB | Fits | Get file → | |
| Q5_0 | 0.8 GB | 2.4 GB | Fits | Get file → | |
| Q5_K_S | 0.9 GB | 2.4 GB | Fits | Get file → | |
| Q5_K_M | 0.9 GB | 2.4 GB | Fits | Get file → | |
| Q5_1 | 0.9 GB | 2.5 GB | Fits | Get file → | |
| Q5_K_L | 0.9 GB | 2.5 GB | Fits | Get file → | |
| Q6_K_M | 1.0 GB | 2.5 GB | Fits | Get file → | |
| Q6_K_L | 1.0 GB | 2.6 GB | Fits | Get file → | |
| Q8_0 | 1.2 GB | 2.8 GB | Fits | Get file → | |
| BF16 | 2.3 GB | 3.9 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_1 (0.73 GB) or Q4_K_M (0.74 GB). For 4 GB VRAM, use IQ3_M (0.57 GB) or Q3_K_S (0.62 GB). For 2 GB VRAM, use IQ3_S (0.57 GB) or Q3_K_S (0.62 GB). Memory estimates are approximate.
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 BF16 (2.3 GB file, about 3.9 GB in use).
Which LFM2.5-Audio-1.5B quant should you choose?
Q4_K_M is the usual starting point for LFM2.5-Audio-1.5B: it balances file size and quality well. Here it is a 0.7 GB file.
The Q8_0 file is 1.2 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 the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about LFM2.5-Audio-1.5B
How much VRAM does LFM2.5-Audio-1.5B need?
About 2.3 GB at Q4_K_M with an 8K context window. That is the 0.7 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 LFM2.5-Audio-1.5B on an 8 GB GPU?
Yes, with BF16: the 2.3 GB file needs about 3.9 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: file is 0.0 GB, IQ3_M is 0.6 GB, IQ3_S is 0.6 GB, Q3_K_S is 0.6 GB, Q3_K_M is 0.6 GB, Q4_0 is 0.7 GB and 16 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 1.1 GB at 8K and 4.3 GB at 32K.
Where can I download LFM2.5-Audio-1.5B GGUF?
The files are on Hugging Face in the Mungert/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, using Q4_1 or Q4_K_M quantizations will fit within 8 GB VRAM with an estimated 2.3 GB usage at 8k context.
Does the model support multiple languages?
The model supports English only; no other languages are supported.
Can I use the model for vision tasks?
No, the model does not have vision capabilities.