LFM3 Omni 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 Omni 2B – omni‑modal model for text, image, video and audio
LFM3 Omni 2B is a 2.17B parameter model that understands text, images, video and audio, and can output text or speech. It is designed for on‑device use and supports real‑time voice conversations via llama.cpp.
Good at
- Omni‑modal understanding
- Text and speech output
- Real‑time voice conversations
Limits
- No reasoning mode in llama‑server
- Requires llama.cpp v0.8.0 or newer
- License is other
Best for
- On‑device chat with voice
- Transcribe or translate speech
- Answer questions about video content
Who it’s for. Developers building edge applications that need a single model for text, vision, audio and speech. Suitable for phones, laptops and other hardware with limited resources.
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 memory at 8k context). For 16 GB VRAM, Q8_0 (1.85 GB, ~4 GB memory) or BF16/F16 (3.47 GB, ~5.6 GB memory). Estimates are approximate.
What GPU do you need for LFM3 Omni 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 Omni 2B quant should you choose?
Q4_K_M is the usual starting point for LFM3 Omni 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 Omni 2B
How much VRAM does LFM3 Omni 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 Omni 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 Omni 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 Omni 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 Omni 2B GGUF?
The files are on Hugging Face in the LiquidAI/LFM3-Omni-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 Omni 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 Omni 2B on 8 GB VRAM?
Yes, use the Q4_0 or Q4_K_M quantized file, which is about 1.05–1.1 GB and requires roughly 3.2 GB of VRAM at 8k context.
Does the model support real‑time voice conversation?
Yes, when used with llama‑server and the /v1/realtime WebSocket API, it can handle real‑time voice conversations with tool calls.
What context length does the model support?
The model supports a context length of 32K tokens (input plus output).