D1 Omni 2B needs about 5.6 GB of memory at BF16 (a 3.5 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 3 quants, from 1.8 GB (Q8_0) to 3.5 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.
Decision model for text, pictures, and audio with calibrated answers
D1 Omni 2B is a decision model built on LFM3-Omni-2B. It returns calibrated answers in one forward pass without generating tokens. The model supports text, pictures, audio, and video inputs.
Good at
- Fast decisions (5.8 ms on H100)
- Multi‑modal input handling
- Calibrated probability outputs
Limits
- No generation of tokens
- Limited to supported question types in llama.cpp
- Requires ffmpeg for video
Best for
- Real‑time call analysis
- Voice‑enabled decision systems
- Rapid multi‑modal inference
Who it’s for. Developers needing quick, calibrated decisions from text, images, or audio. Suitable for applications that require no token generation and can run on local CPUs or GPUs.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| 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 Q8_0 (1.85 GB, ~4 GB memory at 8k context). For 16 GB VRAM, BF16 or F16 (3.47 GB, ~5.6 GB memory) provide higher precision. Memory estimates are approximate.
What GPU do you need for D1 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 D1 Omni 2B quant should you choose?
BF16 (3.5 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 1.8 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 D1 Omni 2B
How much VRAM does D1 Omni 2B need?
About 5.6 GB at BF16 with an 8K context window. That is the 3.5 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 D1 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 D1 Omni 2B GGUF?
It depends on the quant: Q8_0 is 1.8 GB, BF16 is 3.5 GB, F16 is 3.5 GB.
What context length does D1 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 D1 Omni 2B GGUF?
The files are on Hugging Face in the LiquidAI/d1-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 D1 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 D1 Omni 2B on 8 GB VRAM?
Yes, the Q8_0 quantized model is 1.85 GB and requires about 4 GB of VRAM at 8k context.
Does the model support video input?
Video is read as frames and requires ffmpeg in PATH, but full support is limited in llama.cpp.
What languages does the model understand?
The model supports English, Arabic, Chinese, French, German, Italian, Japanese, Korean, Portuguese, Spanish, Vietnamese, Thai, Indonesian, Hindi, Russian, and Polish.