OpenDecider — local AI model by Manjunath Janardhan
Written by Jakub Rusinowski · Last updated
Open decision models distilled from calibrated teachers: a 400M encoder (nano) and a 4B LoRA on Qwen3-4B (small), installed with pip and served by opendecider serve, a /v1/systemone drop-in. Larger 30B and 80B MoE variants need NVIDIA GPUs and are not listed here.
Variants
The smallest OpenDecider variant needs about 1 GB of VRAM at Q4_K_M — quantized weights plus framework overhead, before any KV cache.
| Model | VRAM at Q4 | VRAM | Context | Run it |
|---|---|---|---|---|
| OpenDecider-nano → 0.4B | ~1 GB | Not published | opendecider serve :8000 | |
| OpenDecider-small → 4B | ~3.3 GB | Not published | opendecider serve :8000 | |
| OpenDecider-small MLX 4-bit → 4B | ~3.2 GB | Not published | opendecider (MLX) |
Memory is quantized weights plus overhead at Q4_K_M, from the same engine as the GPU & VRAM checker.
How to run OpenDecider locally
Install Ollama, then pull the tag.
Served by opendecider serve (default port 8000). This model does not run in Ollama.
Pick a size above for its own VRAM figure, speed estimate and install command.
Licence
Commercial use permitted. No usage restrictions beyond attribution.
Applies to: OpenDecider-nano, OpenDecider-small, OpenDecider-small MLX 4-bitRecommended GPU
The cheapest catalogued GPU that runs OpenDecider locally (min 1 GB VRAM) is the Intel Arc B570 (10 GB).
OpenDecider — frequently asked questions
How much VRAM does OpenDecider need?
OpenDecider needs about 1 GB VRAM at Q4_K_M quantization for its smallest variant. Variants: OpenDecider-nano (1 GB, Q4_K_M); OpenDecider-small (3 GB, Q4_K_M); OpenDecider-small MLX 4-bit (3 GB, Q4_K_M). On Apple Silicon, unified memory counts toward this requirement.
Can I run OpenDecider on an RTX 4090 (24 GB)?
Yes — OpenDecider 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 OpenDecider?
Q4_K_M is the best balance of quality and VRAM for OpenDecider 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 OpenDecider locally?
OpenDecider 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.