Decider — lokalny model AI od Mapika
Autor: Jakub Rusinowski · Ostatnia aktualizacja:
Rodzina otwartych modeli decyzyjnych na bazach Qwen3.5 (od 0,8B do 35B-A3B) z jednym interfejsem, do 255 opcji na pytanie i serwerem zgodnym z TypeSafe.
Warianty
Najmniejszy wariant Decider 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 |
|---|---|---|---|---|
| Decider 0.8B 0.8B | ~1.3 GB | Not published | decider.serve | |
| Decider 2B → 2B | ~2.2 GB | 32K | decider.serve | |
| Decider 4B → 4B | ~3.6 GB | Not published | decider.serve | |
| Decider 35B-A3B (NVFP4) → 35B (3B active) | ~22.5 GB | Not published | decider.serve |
Pamięć to skwantyzowane wagi plus narzut przy Q4_K_M, liczone tym samym silnikiem co sprawdzarka GPU i VRAM.
Jak uruchomić Decider lokalnie
Zainstaluj Ollama, a potem pobierz tag.
Served by decider.serve. 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: Decider 0.8B, Decider 2B, Decider 4B, Decider 35B-A3B (NVFP4)Polecane GPU
Najtańsze GPU z naszego katalogu, które uruchomi Decider lokalnie (min. 1 GB VRAM), to Intel Arc B570 (10 GB).
Decider — najczęściej zadawane pytania
How much VRAM does Decider need?
Decider needs about 1 GB VRAM at Q4_K_M quantization for its smallest variant. Variants: Decider 0.8B (1 GB, Q4_K_M); Decider 2B (2 GB, Q4_K_M); Decider 4B (4 GB, Q4_K_M); Decider 35B-A3B (NVFP4) (23 GB, Q4_K_M). On Apple Silicon, unified memory counts toward this requirement.
Can I run Decider on an RTX 4090 (24 GB)?
Yes — Decider 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 Decider?
Q4_K_M is the best balance of quality and VRAM for Decider 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 Decider locally?
Decider 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.