vllm-d3-lite needs about 2.0 GB of memory at Q8_0 (a 1.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 1.1 GB (Q8_0) to 2.0 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.
vllm-d3-lite: 1.01B multimodal decision model
vllm-d3-lite is a 1.01B parameter Qwen‑35 architecture model designed for decision tasks. It accepts text, images, and videos, returning probabilities for multiple-choice, yes/no, or score questions in a single call.
Good at
- Multimodal decision making
- Fast inference on GPUs
- Single-call multiple question support
Limits
- No text generation
- Requires 8k context for memory estimates
- License is Apache‑2.0
Best for
- Rapid decision pipelines
- Batching multiple-choice queries
- Vision‑enabled QA
Who it’s for. Developers building decision‑oriented services that need quick, probabilistic answers from text and media. The model is ideal for applications where generation is not required, but inference speed and multimodal input handling are critical.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 1.1 GB | 2.0 GB | Fits | Get file → | |
| BF16 | 2.0 GB | 2.9 GB | Fits | Get file → |
For 8 GB VRAM, use Q8_0 (1.08 GB file, ~2 GB memory at 8k context). If 16 GB VRAM is available, BF16 (2.03 GB file, ~2.9 GB memory at 8k context) offers higher precision. Memory estimates are approximate.
What GPU do you need for vllm-d3-lite?
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 (2.0 GB file, about 2.9 GB in use).
Which vllm-d3-lite quant should you choose?
Q8_0 (1.1 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about vllm-d3-lite
How much VRAM does vllm-d3-lite need?
About 2.0 GB at Q8_0 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 vllm-d3-lite on an 8 GB GPU?
Yes, with BF16: the 2.0 GB file needs about 2.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of vllm-d3-lite GGUF?
It depends on the quant: Q8_0 is 1.1 GB, BF16 is 2.0 GB.
What context length does vllm-d3-lite support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.4 GB at 8K and 1.6 GB at 32K.
Where can I download vllm-d3-lite GGUF?
The files are on Hugging Face in the ggml-org/vllm-d3-lite-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 vllm-d3-lite use?
Hugging Face lists the license as apache-2.0. 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 vllm-d3-lite on 8 GB VRAM?
Yes, the Q8_0 quantization uses about 2 GB of VRAM at 8k context, fitting within 8 GB.
Does this model support text generation?
No, it is a decision model and does not generate text.
What license applies to vllm-d3-lite?
The model is released under the Apache‑2.0 license.