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 4 quants, from 1.1 GB (Q4_K_M) to 3.5 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.
Decision model for text, pictures, and video with calibrated answers
d1 2B is a decision model built on LFM3-VL-2B. It returns calibrated answers in one 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 token generation
- Vision support limited to llama.cpp v0.8.0+
- License is LFM Open License v1.0
Best for
- Routing and triage
- Moderation and guardrails
- Intent and topic classification
Who it’s for. Engineers building pipelines that require quick, calibrated decisions over text, images, or video. Suitable for moderation, routing, and extraction tasks where token generation is unnecessary.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 1.1 GB | 3.2 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 → | |
| F16 | 3.5 GB | 5.6 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_M (1.1 GB, 3.2 GB memory at 8K context). For 12 GB VRAM, Q8_0 (1.85 GB, 4 GB memory) is suitable. For 24 GB VRAM, BF16 or F16 (3.47 GB, 5.6 GB memory) can be used.
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 1.7 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 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: Q4_K_M is 1.1 GB, Q8_0 is 1.8 GB, BF16 is 3.5 GB, F16 is 3.5 GB.
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 LiquidAI/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, the Q4_K_M quantized model is 1.1 GB and requires about 3.2 GB of VRAM at 8K context.
Does d1 2B support video input?
Video input is supported via llama.cpp, but requires ffmpeg in PATH and is not yet supported for multiple choice or extraction.
What languages does d1 2B understand?
It supports English, Arabic, Chinese, French, German, Italian, Japanese, Korean, Portuguese, Spanish, Vietnamese, Thai, Indonesian, Hindi, Russian, and Polish.