jev control core needs about 2.4 GB of memory at F16 (a 1.5 GB file) with an 8K context window, so it fits on a 4 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.
A lightweight decision model for agent decision sites
jev control core is a small, fast decision model based on Qwen3.5-0.8B-Base. It is designed for short state, 2‑5 option decisions inside larger agent loops. The model is available in a single F16 GGUF file.
Good at
- Decision routing
- Tool selection
- Moderation gating
Limits
- No vision support
- Requires 8‑k context for memory estimate
- Apache‑2.0 license
Best for
- Guardrail injection
- Context ranking
- Entity matching
Who it’s for. Developers building agent systems that need quick, low‑latency decision points. The model is ideal for integrating into larger LLM pipelines where only text decisions are required.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| F16 | 1.5 GB | 2.4 GB | Fits | Get file → |
The only available quant is F16, 1.52 GB. It requires approximately 2.4 GB of VRAM at 8‑k context. For 8 GB VRAM, this quant is suitable. No other quants are provided.
What GPU do you need for jev control core?
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 F16 (1.5 GB file, about 2.4 GB in use).
Which jev control core quant should you choose?
F16 (1.5 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about jev control core
How much VRAM does jev control core need?
About 2.4 GB at F16 with an 8K context window. That is the 1.5 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 jev control core on an 8 GB GPU?
Yes, with F16: 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 jev control core GGUF?
It depends on the quant: F16 is 1.5 GB.
What context length does jev control core 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 jev control core GGUF?
The files are on Hugging Face in the abhishek085/jev-control-core repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does jev control core 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 jev control core on 8 GB VRAM?
Yes, the F16 quant requires about 2.4 GB of VRAM at 8‑k context, which fits within an 8 GB GPU.
Does jev control core support vision?
No, the model is a text‑only decoder and does not include vision capabilities.