OpenJev — local AI model by openjev (community)
Written by Jakub Rusinowski · Last updated
A 27B open decision model for text, web pages and screenshots, with up to 52 options a question. llama.cpp's server runs it natively from the ggml-org GGUF. Weights are CC-BY-NC-4.0: non-commercial use only.
Variants
The smallest OpenJev variant needs about 20 GB of VRAM at Q4_K_M — quantized weights plus framework overhead, before any KV cache.
| Model | VRAM at Q4 | VRAM | Context | Run it |
|---|---|---|---|---|
| OpenJev 27B → 27B | ~20.2 GB | Not published | llama-server (llama.cpp) :9931 |
Memory is quantized weights plus overhead at Q4_K_M, from the same engine as the GPU & VRAM checker.
How to run OpenJev locally
Install Ollama, then pull the tag.
Served by llama-server (llama.cpp) (default port 9931). This model does not run in Ollama.
Pick a size above for its own VRAM figure, speed estimate and install command.
Licence
Research / non-commercial only — this licence does NOT permit shipping a commercial product.
Applies to: OpenJev 27BRecommended GPU
The cheapest catalogued GPU that runs OpenJev locally (min 20 GB VRAM) is the AMD Radeon RX 7900 XTX (24 GB).
OpenJev — frequently asked questions
How much VRAM does OpenJev need?
OpenJev needs about 20 GB VRAM at Q4_K_M quantization for its smallest variant. Variants: OpenJev 27B (20 GB, Q4_K_M). On Apple Silicon, unified memory counts toward this requirement.
Can I run OpenJev on an RTX 4090 (24 GB)?
Yes — OpenJev runs on an RTX 4090 (24 GB) and other 24 GB cards such as the RTX 3090. Smaller variants also fit comfortably on 8–16 GB GPUs at Q4_K_M.
What quantization should I use for OpenJev?
Q4_K_M is the best balance of quality and VRAM for OpenJev in most cases. Choose Q8_0 for near-lossless quality if you have spare VRAM, or smaller quants (Q3/Q2) only when memory is tight.
How do I run OpenJev locally?
OpenJev is a decision model: it is called over an HTTP endpoint (/v1/systemone), not chatted with. Where a variant is available in Ollama 0.35 or newer, pull it with `ollama pull` and send requests to the local server; the others ship their own server. Each variant page shows the exact commands for that model.