vev 4b Q4 K M needs about 4.3 GB of memory at Q4_K_M (a 2.7 GB file) with an 8K context window, so it fits on a 6 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 4.4 GB.
vev 4b Q4 K M – a Qwen3.5‑based model that can answer yes/no, multiple‑choice and graded questions and process images
vev 4b Q4 K M is a 4.21 b parameter model based on Qwen3.5. It supports vision and can answer structured queries about text, JSON or images. The model is released under CC BY‑NC 4.0 and is intended for non‑commercial use.
Good at
- Structured yes/no and multiple‑choice queries
- Image‑based question answering
- Probabilistic answer ranking
Limits
- Requires NVIDIA GPU with ~10 GB free VRAM
- No vision support in the base model card excerpt
- CC BY‑NC 4.0 license limits commercial use
Best for
- Rapid prototyping of decision‑making agents
- Testing image‑question pipelines
- Research on multimodal LLMs
Who it’s for. Developers building non‑commercial prototypes that need a lightweight multimodal LLM. Researchers exploring vision‑enabled decision models can use this checkpoint for experimentation.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 2.7 GB | 4.3 GB | Fits | Get file → |
The Q4_K_M quantization file is 2.71 GB and needs about 4.3 GB of RAM at 8 k context. For 8 GB VRAM GPUs, this quant is suitable. If more VRAM is available, the same quant can handle larger contexts up to the trained 262,144 tokens.
What GPU do you need for vev 4b Q4 K M?
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: no quant fits at an 8K context.
- 6 GB VRAM: the best quant that fits is Q4_K_M (2.7 GB file, about 4.3 GB in use).
Which vev 4b Q4 K M quant should you choose?
Q4_K_M is the usual starting point for vev 4b Q4 K M: it balances file size and quality well. Here it is a 2.7 GB file.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about vev 4b Q4 K M
How much VRAM does vev 4b Q4 K M need?
About 4.3 GB at Q4_K_M with an 8K context window. That is the 2.7 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 vev 4b Q4 K M on an 8 GB GPU?
Yes, with Q4_K_M: the 2.7 GB file needs about 4.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of vev 4b Q4 K M GGUF?
It depends on the quant: Q4_K_M is 2.7 GB.
What context length does vev 4b Q4 K M support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.4 GB at 32K.
Where can I download vev 4b Q4 K M GGUF?
The files are on Hugging Face in the SuperPauly/vev-4b-Q4_K_M-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 vev 4b Q4 K M use?
Hugging Face lists the license as cc-by-nc-4.0. 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 vev 4b Q4 K M on 8 GB VRAM?
Yes, the Q4_K_M quant requires about 4.3 GB of RAM at 8 k context, which fits within 8 GB VRAM with headroom for other processes.
Does this model support vision?
Yes, it can process images as part of the input state and answer image‑related questions.
Is this model free for commercial use?
No, it is released under CC BY‑NC 4.0, which allows non‑commercial use only.