d1-omni-600M needs about 1.4 GB of memory at Q4_K_M (a 0.3 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 5 quants, from 0.3 GB (Q4_K_M) to 0.8 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.4 GB.
d1-omni-600M: a 587M‑parameter decision model for vision, audio, and text
d1-omni-600M is a 587M‑parameter decision model built on LFM2.5‑Encoder‑350M. It accepts text, images, or up to 30 s of speech and returns typed answers with zero output tokens. The model is not a chat model and does not generate text.
Good at
- Vision‑language decisions
- Audio‑language classification
- Zero‑token typed answers
Limits
- Context length 16,384 tokens
- No generation capability
- Requires llama.cpp for inference
Best for
- Routing and triage
- Moderation and intent classification
- Visual inspection and agent guardrails
Who it’s for. Developers needing fast, deterministic yes/no or choice decisions from multimodal inputs. The model is ideal for pipelines that require no text generation and can handle text, image, or audio in a single forward pass.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 0.3 GB | 1.4 GB | Fits | Get file → | |
| Q5_K_M | 0.3 GB | 1.4 GB | Fits | Get file → | |
| Q6_K | 0.3 GB | 1.5 GB | Fits | Get file → | |
| Q8_0 | 0.4 GB | 1.5 GB | Fits | Get file → | |
| BF16 | 0.8 GB | 1.9 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_M (0.26 GB file, ~1.4 GB memory at 8 k context) or Q5_K_M (0.29 GB file, ~1.4 GB memory). For 16 GB VRAM, Q6_K (0.35 GB file, ~1.5 GB memory) or Q8_0 (0.41 GB file, ~1.5 GB memory) are suitable. BF16 requires ~1.9 GB memory and a larger file.
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?
Q4_K_M is the usual starting point for d1-omni-600M: it balances file size and quality well. Here it is a 0.3 GB file.
The Q8_0 file is 0.4 GB, about 1.6 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.
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 1.4 GB at Q4_K_M with an 8K context window. That is the 0.3 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: Q4_K_M is 0.3 GB, Q5_K_M is 0.3 GB, Q6_K is 0.3 GB, Q8_0 is 0.4 GB, BF16 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 AtomicChat/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, using Q4_K_M or Q5_K_M quantizations. Each file is 0.26 GB or 0.29 GB and requires about 1.4 GB VRAM at 8 k context.
Does the model support text generation?
No. The model returns typed answers directly from its distribution; it does not generate text.
What is the maximum context length?
The model supports 16,384 tokens, combining text, image, and audio positions.