Decider 2B — VRAM & /v1/systemone setup
Written by Jakub Rusinowski · Last updated
Mapika's 2B decision model on Qwen3.5-2B-Base, served by decider.serve with a TypeSafe-compatible /v1/systemone.
Decider 2B needs about 2 GB of VRAM at Q4_K_M — quantized weights plus framework overhead, before any KV cache. On Apple Silicon that figure comes out of unified memory.
Call Decider 2B
Served by decider.serve. This model does not run in Ollama.
Setup for servers other than Ollama →
Build a request for this model Decision models guide
Other decision models: Nimble 9B · Tev1 4B · Tev1 0.8B · Winnow 12B · Winnow E4B · Decider 4B · Decider 35B-A3B (NVFP4) · JevK5 4B · Intern-Decision 4B · AutoJev 27B · Laya
Hardware fit
Weights plus overhead plus the KV cache at a 8,192-token prompt, on NVIDIA RTX 4090 (24 GB). A publisher build is sized from its file; the other rows are modelled at a standard quant. Decision requests are short, so no long-context figure is shown.
| Quant | Memory | VRAM | Fit |
|---|---|---|---|
| BF16 Publisher build · 3.8 GB file | 5.4 GB | Fits | |
| Q4_K_M 4.83 bpw · modelled quant | 2.9 GB | Fits | |
| Q6_K 6.56 bpw · modelled quant | 3.4 GB | Fits | |
| Q8_0 8.50 bpw · modelled quant | 4 GB | Fits |
Published file size: BF16 3.8 GB. A download size from the model publisher — not a VRAM requirement.
Needs torch, transformers>=5, flash-linear-attention (optional but several times faster). typesafe-sdk works against decider.serve via TYPESAFE_BASE_URL. Current revision v11; v10 available as a tag.
How it was scored
Two different suites on two different scales. Never compare the numbers across the two cards.
Decision Index 0.2.1 (snapshot 2026-09-28)
Decision Index 0.2.1- ECE (lower is better)
- 0.0771
- Median compute
- 8.1 ms on 1x NVIDIA RTX PRO 6000 (96 GB)
Community-maintained; not affiliated with the model authors.
Source ↗Decision models are not ranked on chat, creative or coding scores.
Specifications
Verified — Checked against the primary source — the model card or the vendor spec page — and corroborated by a second independent source.
- Parameters
- 2.27B
- Context window
- 32K
- Architecture
- Fine-tune of Qwen/Qwen3.5-2B-Base
- Provider
- Mapika
- Licence
- Apache-2.0
- Specified at
- Q4_K_M
- System RAM
- 8 GB
- Record updated
- 2026-09-30
Commercial use permitted. No usage restrictions beyond attribution.
Other Decider sizes
Decider 2B — frequently asked questions
What is Decider 2B?
Decider 2B is a decision model: you send it a state and typed questions (choice, yes/no/unknown, or a score) and it returns one answer per question with a probability for every option. It is not a chat model.
How do I run Decider 2B locally?
Decider 2B does not run in Ollama. Served by decider.serve. This model does not run in Ollama. See the setup guide for servers other than Ollama.
How much memory does Decider 2B need?
About 2 GB for the weights plus overhead at Q4_K_M, before the prompt's KV cache. Decision prompts are short, so the cache stays small.
How accurate is Decider 2B?
It has two separate published scores on two different suites — the author's own benchmark and the community Decision Index 0.2.1. They are not comparable with each other, and neither is a calibration guarantee.