OpenDecider — lokalny model AI od Manjunath Janardhan
Autor: Jakub Rusinowski · Ostatnia aktualizacja:
Otwarte modele decyzyjne destylowane z kalibrowanych modeli-nauczycieli: enkoder 400M (nano) i 4B LoRA na Qwen3-4B (small), instalowane przez pip i obsługiwane przez opendecider serve zgodny z /v1/systemone. Większe warianty MoE 30B i 80B wymagają GPU NVIDIA i nie są tu wymienione.
Warianty
Najmniejszy wariant OpenDecider potrzebuje około 1 GB VRAM przy Q4_K_M — skwantyzowane wagi plus narzut frameworka, bez pamięci podręcznej KV.
| Model | VRAM przy Q4 | VRAM | Kontekst | Uruchom |
|---|---|---|---|---|
| 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) |
Pamięć to skwantyzowane wagi plus narzut przy Q4_K_M, liczone tym samym silnikiem co sprawdzarka GPU i VRAM.
Jak uruchomić OpenDecider lokalnie
Zainstaluj Ollama, a potem pobierz tag.
Served by opendecider serve (default port 8000). This model does not run in Ollama.
Wybierz rozmiar powyżej, aby zobaczyć jego VRAM, szacowaną szybkość i polecenie instalacji.
Licencja
Commercial use permitted. No usage restrictions beyond attribution.
Dotyczy: OpenDecider-nano, OpenDecider-small, OpenDecider-small MLX 4-bitPolecane GPU
Najtańsze GPU z naszego katalogu, które uruchomi OpenDecider lokalnie (min. 1 GB VRAM), to Intel Arc B570 (10 GB).
OpenDecider — najczęściej zadawane pytania
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.