d1 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 7 quants, from 1.0 GB (IQ3_S) to 3.5 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.
d1 2B – a decision model for text, images, and video
d1 2B is a decision model built on LFM3-VL-2B. It returns calibrated answers in a single forward pass without generating tokens. The model supports reasoning, tools, and vision.
Good at
- Fast decisions in milliseconds
- Calibrated probability outputs
- Multi-modal input handling
Limits
- No text generation
- Requires llama.cpp build with d1 / LFM3 decision path
- License is LFM Open License v1.0
Best for
- Routing and triage
- Moderation and guardrails
- Intent and topic classification
Who it’s for. Developers building pipelines that need quick, accurate decisions over text, images, or video. The model is suitable for moderation, classification, and extraction tasks where token generation is unnecessary.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ3_S | 1.0 GB | 3.1 GB | Fits | Get file → | |
| IQ4_XS | 1.1 GB | 3.2 GB | Fits | Get file → | |
| Q4_K_M | 1.1 GB | 3.2 GB | Fits | Get file → | |
| Q5_K_M | 1.3 GB | 3.4 GB | Fits | Get file → | |
| Q6_K | 1.5 GB | 3.7 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 → |
For 8 GB VRAM, use IQ4_XS or Q4_K_M (file size 1.05 GB or 1.12 GB, memory ~3.2 GB). For 12 GB VRAM, Q5_K_M or Q6_K (1.29 GB or 1.55 GB, memory ~3.4–3.7 GB). BF16 requires 3.47 GB and ~5.6 GB memory, suitable for larger GPUs.
What GPU do you need for d1 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 2B quant should you choose?
Q4_K_M is the usual starting point for d1 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 1.6 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.
If memory is tight, the smallest file is IQ3_S at 1.0 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about d1 2B
How much VRAM does d1 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 d1 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 2B GGUF?
It depends on the quant: IQ3_S is 1.0 GB, IQ4_XS is 1.1 GB, Q4_K_M is 1.1 GB, Q5_K_M is 1.3 GB, Q6_K is 1.5 GB, Q8_0 is 1.8 GB and 1 more.
What context length does d1 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 2B GGUF?
The files are on Hugging Face in the AtomicChat/d1-2B-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 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 2B on 8 GB VRAM?
Yes, use IQ4_XS or Q4_K_M quantizations; they fit within 8 GB VRAM and use about 3.2 GB memory at 8K context.
Does d1 2B support image input?
Yes, the vision projector mmproj-d1-2B-F16.gguf is included, enabling image and text input.
Is d1 2B capable of generating text?
No, d1 2B is a decision model and does not generate tokens; it returns typed answers with probabilities.