# d1-Omni-2B

> d1-Omni-2B is a decision model for text, pictures, and audio, built on LFM3-Omni-2B. It returns calibrated answers in one forward pass, without generating tokens.

- **Organisation:** LiquidAI
- **Category:** Omni / Any-to-Any
- **Parameters:** 2.2B
- **Context length:** 128,000 tokens
- **Licence:** lfm1.0 (Commercial use with conditions)
- **Released:** 2026-10-24
- **Hugging Face:** 6.8K downloads (30 days), 131 likes
- **Ollama:** `ollama run d1-omni:2b`

## Estimated memory

| Quant | ≈ GB |
|---|---|
| Q2_K | 1.57 |
| Q3_K_M | 1.91 |
| Q4_K_M | 2.16 |
| Q5_K_M | 2.38 |
| Q6_K | 2.62 |
| Q8_0 | 3.13 |
| F16 | 5.11 |

## Runs with

- [llama.cpp](https://selfhost.directory/project/llamacpp)
- [MLX](https://github.com/ml-explore/mlx-lm)
- [Ollama](https://selfhost.directory/project/ollama)
- [Transformers](https://github.com/huggingface/transformers)
- [ONNX Runtime](https://onnxruntime.ai) (community)

## About

d1-Omni-2B is a decision model for text, pictures, and audio, built on LFM3-Omni-2B. It returns calibrated answers in one forward pass, without generating tokens.

• Native audio: clips and spoken questions go through the same pass as text and pictures, and spoken questions score within 0.5 points of written ones on unseen tasks.
• Beyond classification: it also extracts text, numbers, and dates with their span, locates objects in pictures, and estimates quantities with an interval.
• Millisecond decisions: 5.8 ms per decision on an NVIDIA H100 and 3.7 ms on an AMD MI325X, or 12.4 ms and 8.2 ms with a 10-second clip.

Find more information about open d1 in our release blog post.

The LFM3 family includes base, text, vision, audio, omni, and decision models. d1-Omni-2B adds audio to d1-2B.

## Alternatives

- [LiquidAI/LFM3-Omni-2B](https://selfhost.directory/models/liquidai/lfm3-omni-2b) (2.2B, lfm1.0, ≈2.16 GB at Q4): LFM3-Omni-2B is Liquid AI's first omni-modal model in the LFM3 family: a single end-to-end model that understands text, images, video and audio, and answers in text and speech. It is built for on-device use: one model replaces a separate ASR model, vision-language model, LLM and TTS model.
- [LiquidAI/LFM3-Audio-2B](https://selfhost.directory/models/liquidai/lfm3-audio-2b) (2B, lfm1.0, ≈2.2 GB at Q4): LFM3-Audio-2B is a compact, fully featured audio model that runs locally on laptops and edge devices. It takes text or audio as input and responds with text, speech, or both.
- [google/gemma-4-E2B-it](https://selfhost.directory/models/google/gemma-4-e2b-it) (5.1B, Apache 2.0, ≈3.81 GB at Q4): Gemma is a family of open models built by Google DeepMind. Gemma 4 models are multimodal, handling text and image input (with audio supported on E2B, E4B, and 12B) and generating text output. This release includes open-weights models in both pre-trained and instruction-tuned variants.
- [google/gemma-4-E4B-it](https://selfhost.directory/models/google/gemma-4-e4b-it) (8B, Apache 2.0, ≈5.9 GB at Q4): Gemma is a family of open models built by Google DeepMind. Gemma 4 models are multimodal, handling text and image input (with audio supported on E2B, E4B, and 12B) and generating text output. This release includes open-weights models in both pre-trained and instruction-tuned variants.
- [google/gemma-4-E2B](https://selfhost.directory/models/google/gemma-4-e2b) (5.1B, Apache 2.0, ≈3.81 GB at Q4): Gemma is a family of open models built by Google DeepMind. Gemma 4 models are multimodal, handling text and image input (with audio supported on E2B, E4B, and 12B) and generating text output. This release includes open-weights models in both pre-trained and instruction-tuned variants.
- [deepseek-ai/Janus-1.3B](https://selfhost.directory/models/deepseek-ai/janus-1.3b) (2.1B, MIT, ≈3.24 GB at Q4): Janus is a novel autoregressive framework that unifies multimodal understanding and generation. It addresses the limitations of previous approaches by decoupling visual encoding into separate pathways, while still utilizing a single, unified transformer architecture for processing.

More: https://selfhost.directory/models/liquidai/d1-omni-2b/alternatives

## Runs well on

- [GeForce RTX 4060](https://selfhost.directory/models/liquidai/d1-omni-2b/on/rtx-4060): F16, est. 35 tok/s
- [Apple M4 (16 GB)](https://selfhost.directory/models/liquidai/d1-omni-2b/on/apple-m4-16gb): F16, est. 15 tok/s
- [Radeon RX 6700 XT](https://selfhost.directory/models/liquidai/d1-omni-2b/on/rx-6700-xt): F16, est. 49 tok/s
- [GeForce RTX 3060 12GB](https://selfhost.directory/models/liquidai/d1-omni-2b/on/rtx-3060): F16, est. 46 tok/s
- [Arc B580](https://selfhost.directory/models/liquidai/d1-omni-2b/on/arc-b580): F16, est. 58 tok/s
- [Tesla T4](https://selfhost.directory/models/liquidai/d1-omni-2b/on/tesla-t4): F16, est. 41 tok/s

## Similar size

- [LiquidAI/LFM3-Omni-2B](https://selfhost.directory/models/liquidai/lfm3-omni-2b) (2.2B)
- [LiquidAI/LFM3-Audio-2B](https://selfhost.directory/models/liquidai/lfm3-audio-2b) (2B)
- [deepseek-ai/Janus-1.3B](https://selfhost.directory/models/deepseek-ai/janus-1.3b) (2.1B)
- [deepseek-ai/JanusFlow-1.3B](https://selfhost.directory/models/deepseek-ai/janusflow-1.3b) (2B)
- [lmms-lab/Aero-1-Audio](https://selfhost.directory/models/lmms-lab/aero-1-audio) (2.4B)

## FAQ

**How much VRAM does d1-Omni-2B need?**
About 2.2 GB at Q4_K_M with an 8K context. Q8_0 needs about 3.1 GB and full precision about 5.1 GB. Longer contexts need more memory for the KV cache.

**Can d1-Omni-2B run on the RTX 4060?**
Yes. It fits at FP16 / BF16 (about 4.3 GB), at an estimated 35 tokens/s. It fits comfortably on the Apple M4 (16 GB), Radeon RX 6700 XT, RTX 3060 12GB.

**Can I use d1-Omni-2B commercially?**
Yes, with conditions. It is released under lfm1.0. Custom licence: read the model card before using it commercially.

**What is the context length of d1-Omni-2B?**
128,000 tokens (125K). The full window needs far more memory than an 8K context.

**How do I run d1-Omni-2B with Ollama or llama.cpp?**
With Ollama: ollama run d1-omni:2b. With llama.cpp: llama-server -hf Soulfate24/d1-Omni-2B-Paretrix-GGUF:Q4_K_M, which starts an OpenAI-compatible server.

## Links

- huggingface: https://huggingface.co/LiquidAI/d1-Omni-2B
- homepage: https://www.liquid.ai/blog/open-d1
- demo: https://huggingface.co/spaces/multimodalart/jev-decision-index
- ollama: https://ollama.com/library/d1-omni

---
Source: https://selfhost.directory/models/liquidai/d1-omni-2b