Greko 1.7b Beta Merged needs about 2.5 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 10 quants, from 0.8 GB to 1.1 GB (Q4_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.
Greko 1.7b Beta Merged – a compact vision‑language model
Greko 1.7b Beta Merged is a 1.72‑billion‑parameter Qwen3 model merged from Qwen3‑VL‑2B‑Instruct. It supports vision tasks and has a 40960‑token context window. The model is released under the Apache‑2.0 license.
Good at
- Vision‑language understanding
- Long‑context reasoning
- Multilingual text handling
Limits
- No explicit vision‑only support limits
- Requires 8‑k context for memory estimates
- No mention of GPU requirements
Best for
- Mobile offline assistants
- Document analysis on phones
- Image‑to‑text generation
Who it’s for. Developers building offline AI assistants on Android devices. The model is suitable for apps that need vision and text reasoning without internet access.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.8 GB | 2.3 GB | Fits | Get file → | |
| — | 0.8 GB | 2.3 GB | Fits | Get file → | |
| — | 0.8 GB | 2.3 GB | Fits | Get file → | |
| — | 0.8 GB | 2.3 GB | Fits | Get file → | |
| IQ4_NL | 1.1 GB | 2.5 GB | Fits | Get file → | |
| Q4_K_M | 1.1 GB | 2.5 GB | Fits | Get file → | |
| Q4_K_M | 1.1 GB | 2.5 GB | Fits | Get file → | |
| Q4_K_M | 1.1 GB | 2.5 GB | Fits | Get file → | |
| Q4_K_M | 1.1 GB | 2.5 GB | Fits | Get file → | |
| Q4_K_M | 1.1 GB | 2.5 GB | Fits | Get file → |
For 8 GB VRAM, use the Q4_K_M quantized file (1.11 GB, ~2.5 GB memory at 8 k context). For tighter budgets, the unknown quant file (0.82 GB, ~2.3 GB memory) is an option. Estimates are approximate.
What GPU do you need for Greko 1.7b Beta Merged?
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 Q4_K_M (1.1 GB file, about 2.5 GB in use).
Which Greko 1.7b Beta Merged quant should you choose?
Q4_K_M is the usual starting point for Greko 1.7b Beta Merged: it balances file size and quality well. Here it is a 1.1 GB file.
If memory is tight, the smallest file is the first one in the table at 0.8 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Greko 1.7b Beta Merged
How much VRAM does Greko 1.7b Beta Merged need?
About 2.5 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 Greko 1.7b Beta Merged on an 8 GB GPU?
Yes, with Q4_K_M: the 1.1 GB file needs about 2.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Greko 1.7b Beta Merged GGUF?
It depends on the quant: file is 0.8 GB, file is 0.8 GB, file is 0.8 GB, file is 0.8 GB, IQ4_NL is 1.1 GB, Q4_K_M is 1.1 GB and 4 more.
What context length does Greko 1.7b Beta Merged support?
The GGUF header lists a trained context length of 40,960 tokens (40K). The KV cache grows with the context you use: about 0.9 GB at 8K and 3.8 GB at 32K.
Where can I download Greko 1.7b Beta Merged GGUF?
The files are on Hugging Face in the geolazagr/greko repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Greko 1.7b Beta Merged 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 Greko 1.7b on a device with 8 GB VRAM?
Yes, the Q4_K_M quantized file uses about 2.5 GB of VRAM at 8 k context, which fits within 8 GB.
Does the model support vision tasks?
Yes, Greko 1.7b has detected vision abilities and is based on Qwen3‑VL‑2B‑Instruct.
What license applies to this model?
The model is released under the Apache‑2.0 license.