d1-omni-600M needs about 1.9 GB of memory at BF16 (a 0.8 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 3 quants, from 0.4 GB (Q8_0) to 0.8 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.4 GB.
Decision model for text, image, and audio with zero output tokens
d1-omni-600M is a 600M parameter decision model built on LFM2.5-Encoder-350M. It processes text, images, or audio in a single forward pass and returns typed answers without generating text. The model supports vision and audio modalities and is optimized for decision tasks.
Good at
- Zero-token decisions
- Vision‑language and audio‑language support
- Fast inference on GPUs
Limits
- Not a chat model
- Requires 8‑k context for best performance
- Audio limited to 30 s clips
Best for
- Routing and triage
- Moderation and intent classification
- Voice‑command routing
Who it’s for. Developers building pipelines that need quick, typed decisions from multimodal input. It is ideal for applications that require no text generation and rely on deterministic answers.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 0.4 GB | 1.5 GB | Fits | Get file → | |
| BF16 | 0.8 GB | 1.9 GB | Fits | Get file → | |
| F16 | 0.8 GB | 1.9 GB | Fits | Get file → |
For 8 GB VRAM use Q8_0 (0.41 GB, ~1.5 GB memory at 8k context). For 12 GB VRAM use BF16 or F16 (0.76 GB, ~1.9 GB memory). Larger VRAM allows higher context lengths.
What GPU do you need for d1-omni-600M?
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 (0.8 GB file, about 1.9 GB in use).
Which d1-omni-600M quant should you choose?
BF16 (0.8 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 0.4 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-600M
How much VRAM does d1-omni-600M need?
About 1.9 GB at BF16 with an 8K context window. That is the 0.8 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-600M on an 8 GB GPU?
Yes, with BF16: the 0.8 GB file needs about 1.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of d1-omni-600M GGUF?
It depends on the quant: Q8_0 is 0.4 GB, BF16 is 0.8 GB, F16 is 0.8 GB.
What context length does d1-omni-600M support?
The GGUF header lists a trained context length of 128,000 tokens (125K). The KV cache grows with the context you use: about 0.6 GB at 8K and 2.4 GB at 32K.
Where can I download d1-omni-600M GGUF?
The files are on Hugging Face in the LiquidAI/d1-omni-600M-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-600M 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-600M on 8 GB VRAM?
Yes, the Q8_0 quantized model is 0.41 GB and uses about 1.5 GB of VRAM at 8k context.
Does the model support audio input?
Yes, it accepts up to 30 s of 16 kHz mono audio in a single forward pass.
Is the model capable of generating text?
No, it returns typed answers directly from its distribution and does not generate text.