qev 0.8b needs about 1.7 GB of memory at Q8_0 (a 0.8 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 4 quants, from 0.8 GB (Q8_0) to 1.5 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.
qev 0.8b – a small local decision model that returns calibrated probabilities
qev 0.8b is a 0.752 billion‑parameter decision model based on qwen35. It accepts text, JSON or images and returns calibrated probabilities for each option in a single forward pass. The model does not generate text and is optimized for fast inference.
Good at
- Fast single‑pass decision making
- Calibrated probability outputs
- Zero‑shot image support
Limits
- No text generation
- Limited to 262144 context tokens
- Requires 1.3 GB RAM in 8‑bit on a Mac
Best for
- Decision support in local apps
- Rapid probability estimation for user queries
- Image‑based fact checking
Who it’s for. Developers building lightweight decision engines that need fast, calibrated outputs without text generation. Ideal for local inference on modest hardware such as laptops or embedded systems.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 0.8 GB | 1.7 GB | Fits | Get file → | |
| Q8_0 | 0.8 GB | 1.7 GB | Fits | Get file → | |
| Q8_0 | 0.8 GB | 1.7 GB | Fits | Get file → | |
| BF16 | 1.5 GB | 2.4 GB | Fits | Get file → |
For 8‑bit inference use the Q8_0 quantization; the file is 0.81 GB and requires about 1.7 GB of VRAM at 8k context. For higher precision use BF16, 1.52 GB file size and about 2.4 GB VRAM at 8k context. These estimates are approximate.
What GPU do you need for qev 0.8b?
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 (1.5 GB file, about 2.4 GB in use).
Which qev 0.8b quant should you choose?
Q8_0 (0.8 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.
If memory is tight, the smallest file is Q8_0 at 0.8 GB, with the quality trade-offs that come with fewer bits. 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 qev 0.8b
How much VRAM does qev 0.8b need?
About 1.7 GB at Q8_0 with an 8K context window. That is the 0.8 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 qev 0.8b on an 8 GB GPU?
Yes, with BF16: the 1.5 GB file needs about 2.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of qev 0.8b GGUF?
It depends on the quant: Q8_0 is 0.8 GB, Q8_0 is 0.8 GB, Q8_0 is 0.8 GB, BF16 is 1.5 GB.
What context length does qev 0.8b 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 qev 0.8b GGUF?
The files are on Hugging Face in the labqoat/qev-0.8b-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 qev 0.8b 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 qev 0.8b on 8 GB VRAM?
Yes, the Q8_0 quantization requires about 1.7 GB of VRAM at 8k context, well within an 8 GB budget.
Does qev 0.8b support image input?
Yes, images are resized to at most 448×448 (≤196 tokens) and processed zero‑shot via the base model’s vision tower.
Is qev 0.8b capable of text generation?
No, qev 0.8b does not generate text; it only returns calibrated probabilities for each option.