VGPO RL 7B needs about 5.7 GB of memory at Q4_K_M (a 4.7 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 25 quants, from 0.0 GB to 6.3 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 1.9 GB.
VGPO RL 7B – a 7.62B parameter vision‑language model
VGPO RL 7B is a 7.62B parameter qwen2vl model trained with reinforcement learning for visual grounding. It supports reasoning over images and text with a context length of 128000 tokens. The model is released under the MIT license.
Good at
- Visual reasoning
- Image‑guided text generation
- Reinforcement learning fine‑tuning
Limits
- Requires 8.9 GB VRAM for Q4_K_M at 8 k context
- No external vision tokenization beyond mmproj
- No support for non‑image modalities
Best for
- Building image‑captioning pipelines
- Training RL agents for visual tasks
- Deploying on GPU‑limited edge devices
Who it’s for. Developers and researchers who need a vision‑language model with reinforcement learning capabilities. The model is suitable for projects that require reasoning over visual inputs and text in a single inference session.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 1.0 GB | Fits | Get file → | |
| IQ1_S | 1.9 GB | 2.9 GB | Fits | Get file → | |
| IQ1_M | 2.0 GB | 3.0 GB | Fits | Get file → | |
| IQ2_XXS | 2.3 GB | 3.2 GB | Fits | Get file → | |
| IQ2_XS | 2.5 GB | 3.4 GB | Fits | Get file → | |
| IQ2_S | 2.6 GB | 3.6 GB | Fits | Get file → | |
| IQ2_M | 2.8 GB | 3.8 GB | Fits | Get file → | |
| Q2_K_S | 2.8 GB | 3.8 GB | Fits | Get file → | |
| Q2_K | 3.0 GB | 4.0 GB | Fits | Get file → | |
| IQ3_XXS | 3.1 GB | 4.1 GB | Fits | Get file → | |
| IQ3_XS | 3.3 GB | 4.3 GB | Fits | Get file → | |
| Q3_K_S | 3.5 GB | 4.5 GB | Fits | Get file → | |
| IQ3_S | 3.5 GB | 4.5 GB | Fits | Get file → | |
| IQ3_M | 3.6 GB | 4.5 GB | Fits | Get file → | |
| Q3_K_M | 3.8 GB | 4.8 GB | Fits | Get file → | |
| Q3_K_L | 4.1 GB | 5.1 GB | Fits | Get file → | |
| IQ4_XS | 4.2 GB | 5.2 GB | Fits | Get file → | |
| IQ4_NL | 4.4 GB | 5.4 GB | Fits | Get file → | |
| Q4_0 | 4.4 GB | 5.4 GB | Fits | Get file → | |
| Q4_K_S | 4.5 GB | 5.4 GB | Fits | Get file → | |
| Q4_K_M | 4.7 GB | 5.7 GB | Fits | Get file → | |
| Q4_1 | 4.9 GB | 5.8 GB | Fits | Get file → | |
| Q5_K_S | 5.3 GB | 6.3 GB | Fits | Get file → | |
| Q5_K_M | 5.4 GB | 6.4 GB | Fits | Get file → | |
| Q6_K | 6.3 GB | 7.2 GB | Tight | Get file → |
For 8 GB VRAM, use Q4_K_M (file size 4.68 GB, estimated 5.7 GB memory at 8 k context). For 12 GB VRAM, Q5_K_M (5.44 GB, 6.4 GB memory). For 16 GB VRAM, Q6_K (6.25 GB, 7.2 GB memory). The IQ1_S quant (1.9 GB, 2.9 GB memory) is a lightweight option for low‑budget GPUs.
What GPU do you need for VGPO RL 7B?
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 Q2_K (3.0 GB file, about 4.0 GB in use).
- 6 GB VRAM: the best quant that fits is Q4_1 (4.9 GB file, about 5.8 GB in use).
- 8 GB VRAM: the best quant that fits is Q6_K (6.3 GB file, about 7.2 GB in use).
Which VGPO RL 7B quant should you choose?
Q4_K_M is the usual starting point for VGPO RL 7B: it balances file size and quality well. Here it is a 4.7 GB file.
If memory is tight, the smallest file is the first one in the table at 0.0 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 VGPO RL 7B
How much VRAM does VGPO RL 7B need?
About 5.7 GB at Q4_K_M with an 8K context window. That is the 4.7 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 VGPO RL 7B on an 8 GB GPU?
Yes, with Q6_K: the 6.3 GB file needs about 7.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of VGPO RL 7B GGUF?
It depends on the quant: file is 0.0 GB, IQ1_S is 1.9 GB, IQ1_M is 2.0 GB, IQ2_XXS is 2.3 GB, IQ2_XS is 2.5 GB, IQ2_S is 2.6 GB and 19 more.
What context length does VGPO RL 7B support?
The GGUF header lists a trained context length of 128,000 tokens (125K). The KV cache grows with the context you use: about 0.5 GB at 8K and 1.9 GB at 32K.
Where can I download VGPO RL 7B GGUF?
The files are on Hugging Face in the mradermacher/VGPO-RL-7B-i1-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 VGPO RL 7B use?
Hugging Face lists the license as mit. 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 VGPO RL 7B on a GPU with 8 GB VRAM?
Yes, using the Q4_K_M quant which requires about 5.7 GB memory at 8 k context. The file size is 4.68 GB.
Does VGPO RL 7B support vision inputs?
Yes, it is a vision‑language model built on qwen2vl and includes mmproj files for image handling.