AdaVaR 3B needs about 2.7 GB of memory at Q4_K_M (a 1.9 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 12 quants, from 1.3 GB (Q2_K) to 6.2 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.2 GB.
AdaVaR 3B – adaptive visual reasoning with Qwen2VL architecture
AdaVaR 3B is a 3‑billion‑parameter model built on Qwen2VL. It supports vision and text reasoning, with a 128k token context window. The model is released under Apache‑2.0 and available in multiple GGUF quantizations.
Good at
- Vision‑text reasoning
- Adaptive mode selection
- Large context handling
Limits
- No mixture‑of‑experts
- Requires 8k context for memory estimates
- No explicit language list
Best for
- Image‑guided text generation
- Grounded reasoning tasks
- Multimodal chat
Who it’s for. Developers needing a lightweight visual‑reasoning model for local inference. Suitable for research and production environments that can run GGUF files on llama.cpp.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 1.3 GB | 2.1 GB | Fits | Get file → | |
| Q3_K_S | 1.5 GB | 2.3 GB | Fits | Get file → | |
| Q3_K_M | 1.6 GB | 2.4 GB | Fits | Get file → | |
| Q3_K_L | 1.7 GB | 2.5 GB | Fits | Get file → | |
| IQ4_XS | 1.8 GB | 2.6 GB | Fits | Get file → | |
| Q4_K_S | 1.8 GB | 2.6 GB | Fits | Get file → | |
| Q4_K_M | 1.9 GB | 2.7 GB | Fits | Get file → | |
| Q5_K_S | 2.2 GB | 3.0 GB | Fits | Get file → | |
| Q5_K_M | 2.2 GB | 3.0 GB | Fits | Get file → | |
| Q6_K | 2.5 GB | 3.3 GB | Fits | Get file → | |
| Q8_0 | 3.3 GB | 4.1 GB | Fits | Get file → | |
| F16 | 6.2 GB | 7.0 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_M (1.93 GB file, ~2.7 GB memory). For 4 GB VRAM, Q3_K_S (1.45 GB file, ~2.3 GB memory) is recommended. Higher precision quants like F16 need 7 GB memory and are only for high‑end GPUs.
What GPU do you need for AdaVaR 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: the best quant that fits is Q6_K (2.5 GB file, about 3.3 GB in use).
- 6 GB VRAM: the best quant that fits is Q8_0 (3.3 GB file, about 4.1 GB in use).
- 8 GB VRAM: the best quant that fits is F16 (6.2 GB file, about 7.0 GB in use).
Which AdaVaR 3B quant should you choose?
Q4_K_M is the usual starting point for AdaVaR 3B: it balances file size and quality well. Here it is a 1.9 GB file.
The Q8_0 file is 3.3 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.
If memory is tight, the smallest file is Q2_K at 1.3 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about AdaVaR 3B
How much VRAM does AdaVaR 3B need?
About 2.7 GB at Q4_K_M with an 8K context window. That is the 1.9 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 AdaVaR 3B on an 8 GB GPU?
Yes, with F16: the 6.2 GB file needs about 7.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of AdaVaR 3B GGUF?
It depends on the quant: Q2_K is 1.3 GB, Q3_K_S is 1.5 GB, Q3_K_M is 1.6 GB, Q3_K_L is 1.7 GB, IQ4_XS is 1.8 GB, Q4_K_S is 1.8 GB and 6 more.
What context length does AdaVaR 3B support?
The GGUF header lists a trained context length of 128,000 tokens (125K). The KV cache grows with the context you use: about 0.3 GB at 8K and 1.2 GB at 32K.
Where can I download AdaVaR 3B GGUF?
The files are on Hugging Face in the mradermacher/AdaVaR-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 AdaVaR 3B 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 AdaVaR 3B on 8 GB VRAM?
Yes, using Q4_K_M or Q4_K_S quants will fit within 8 GB VRAM with approximate 2.7 GB memory usage.
Does AdaVaR 3B support multiple languages?
The model has no explicit language list; it is trained on multilingual data but language support is not guaranteed.
Is there a vision‑only mode?
AdaVaR 3B includes vision capability but requires image input; it does not provide a dedicated vision‑only mode.