d1 3B needs about 4.2 GB of memory at Q4_K_M (a 1.7 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 4 quants, from 1.7 GB (Q4_K_M) to 5.4 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 8.1 GB.
d1 3B – a multimodal decision model with zero output tokens
d1 3B is a 3.12B parameter decision model built on LFM2.5‑VL‑3B. It accepts text, JSON, or images and returns calibrated, typed answers in a single forward pass with no generated tokens. The model supports a 32,768 token context and is optimized for fast inference on modern GPUs.
Good at
- Fast decision making – 8 ms on RTX 4090
- Multimodal – handles text and images together
- Zero output tokens – efficient for classification tasks
Limits
- No chat or text generation
- Requires a GPU with at least 8 GB VRAM for Q4_K_M
- License is other – check usage rights
Best for
- Routing and triage systems
- Moderation and intent classification
- Visual inspection and guardrails
Who it’s for. Developers building pipelines that need quick, typed decisions over mixed data types. It is ideal for applications that require routing, moderation, or classification without generating text.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 1.7 GB | 4.2 GB | Fits | Get file → | |
| Q8_0 | 2.9 GB | 5.4 GB | Fits | Get file → | |
| BF16 | 5.4 GB | 7.9 GB | Tight | Get file → | |
| F16 | 5.4 GB | 7.9 GB | Tight | Get file → |
For 8 GB VRAM, use Q4_K_M (1.67 GB file, ~4.2 GB memory). If 12 GB VRAM is available, Q8_0 (2.87 GB file, ~5.4 GB memory) offers higher precision. BF16 and F16 require 5.4 GB file and ~7.9 GB memory, suitable for larger GPUs.
What GPU do you need for d1 3B?
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: no quant fits at an 8K context.
- 6 GB VRAM: the best quant that fits is Q8_0 (2.9 GB file, about 5.4 GB in use).
- 8 GB VRAM: the best quant that fits is BF16 (5.4 GB file, about 7.9 GB in use).
Which d1 3B quant should you choose?
Q4_K_M is the usual starting point for d1 3B: it balances file size and quality well. Here it is a 1.7 GB file.
The Q8_0 file is 2.9 GB, about 1.7 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 3B
How much VRAM does d1 3B need?
About 4.2 GB at Q4_K_M with an 8K context window. That is the 1.7 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 3B on an 8 GB GPU?
Yes, with BF16: the 5.4 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of d1 3B GGUF?
It depends on the quant: Q4_K_M is 1.7 GB, Q8_0 is 2.9 GB, BF16 is 5.4 GB, F16 is 5.4 GB.
What context length does d1 3B support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 2.0 GB at 8K and 8.1 GB at 32K.
Where can I download d1 3B GGUF?
The files are on Hugging Face in the LiquidAI/d1-3B-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 3B 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 3B on 8 GB VRAM?
Yes, the Q4_K_M quantized file is 1.67 GB and requires about 4.2 GB of VRAM at 8k context.
Does d1 3B generate text?
No, it returns answers in a single forward pass with zero output tokens.