# iota-decide-4b

Decision models · checked 2026-11-08 · https://dbggr.dev/models/iota-decide-4b/

Open-weight 4B Macrocosmos decision model on Qwen3.5-4B, trained on consumer GPUs

iota-decide-4b is an open-weight decision model from Macrocosmos (Apache 2.0, 4.2B parameters, fine-tuned from Qwen3.5-4B (v0.4) parameters): it answers typed questions, such as yes or no, pick one or pick several, with probabilities instead of writing text. There's no hosted version: you run it on your own hardware. It scores 74.0 (v0.4; self-hosted; seconds are the board's estimate; unranked until the board's 27 Oct draw is equated (the maker's card quotes 78.6)) on the independent JevBench Capability Score (board v1.7.46), where Jev, the reference, scores 77.1.

- Made by: Macrocosmos
- Weights: Open, Apache 2.0
- Size: 4.2B parameters, fine-tuned from Qwen3.5-4B (v0.4)
- Where: Self-host only
- Images: No, text only
- Docs: https://huggingface.co/macrocosm-os/iota-decide-4b-v0.4

## iota-decide-4b price

US dollars per million input tokens. Decision models don't write text, so none of the hosted ones charge for output.

| Where | Input | Output | Notes | Checked |
|---|---|---|---|---|
| Self-host only | Self-host | – | – | [2026-11-08](https://huggingface.co/macrocosm-os/iota-decide-4b-v0.4) |

## iota-decide-4b benchmarks

| Benchmark | Result | What it measures | Reported by |
|---|---|---|---|
| JevBench v1.7.46 | 74.0 | Capability Score: accuracy and calibration on typed decisions, with Jev as the reference system | [Independent](https://benchmarkheaven.com/jev-models) |
| JevBench time | 0.22 s | Seconds per decision: measured end to end for hosted APIs, the board's estimate for self-hosted models | [Independent](https://benchmarkheaven.com/jev-models) |

Makers' speeds are measured on their own hardware and aren't comparable with each other or with JevBench's timings.

## Decision models like iota-decide-4b

| Model | Input / M | JevBench | Weights |
|---|---|---|---|
| iota-decide-4b | Self-host | 74.0 | Open |
| [Piccolo-27B](https://dbggr.dev/models/piccolo-27b/) | Self-host | 86.0 | Open |
| [Mammoth-1](https://dbggr.dev/models/mammoth-1/) | $0.10 | 85.2 | Open |
| [Drex Max v1.1](https://dbggr.dev/models/drex-max-v1-1/) | $0.03 | 84.2 | Closed |
| [Perplexity Decider V1.2](https://dbggr.dev/models/pplx-decider-v1-2/) | $0.02 | 80.8 | Open |
| [d1-ultra](https://dbggr.dev/models/d1-ultra/) | $0.042 | 80.5 | Closed |
| [Kev-27B](https://dbggr.dev/models/kev-27b/) | Self-host | 78.9 | Open |
| [Piccolo-9B](https://dbggr.dev/models/piccolo-9b/) | Self-host | 76.6 | Open |
| [Clef](https://dbggr.dev/models/clef/) | $0.24 | 75.3 | Open |
| [Jev 1.14](https://dbggr.dev/models/jev/) | $0.042 | 75.0 | Closed |
| [d1](https://dbggr.dev/models/d1/) | $0.02 | 74.4 | Closed |
| [Mercury Decide](https://dbggr.dev/models/mercury-decide/) | $0.02 | 73.6 | Closed |
| [Piccolo-4B](https://dbggr.dev/models/piccolo-4b/) | Self-host | 73.6 | Open |
| [OpenAI Decisions (GPT-6 Luna)](https://dbggr.dev/models/openai-decisions/) | $0.10 | 73.5 | Closed |
| [Microsoft-Decision-1](https://dbggr.dev/models/microsoft-decision-1/) | $0.042 | 70.8 | Closed |
| [Elephant-1](https://dbggr.dev/models/elephant-1/) | $0.035 | 70.2 | Open |
| [Strands Decider 26B-A4B](https://dbggr.dev/models/strands-decider-26b-a4b/) | Self-host | 66.7 | Open |
| [Clef-flash](https://dbggr.dev/models/clef-flash/) | $0.038 | 63.8 | Open |
| [Perplexity Decider Flash V1.2](https://dbggr.dev/models/pplx-decider-flash-v1-2/) | $0.01 | 61.7 | Open |
| [Kev-9B](https://dbggr.dev/models/kev-9b/) | Self-host | 61.5 | Open |
| [Clef-omni](https://dbggr.dev/models/clef-omni/) | $0.15 | 58.3 | Open |
| [Joey-1](https://dbggr.dev/models/joey-1/) | $0.01 | 57.8 | Open |
| [d1-3B](https://dbggr.dev/models/d1-3b/) | Self-host | 49.5 | Open |
| [d1-omni-600M (experimental)](https://dbggr.dev/models/d1-omni-600m/) | Self-host | 32.8 | Open |
| [Laya](https://dbggr.dev/models/laya/) | $0.011 | 32.5 | Open |
| [CLM-8B](https://dbggr.dev/models/clm-8b/) | Self-host | 20.1 | Open |
| [Clairic](https://dbggr.dev/models/clairic/) | $0.10 | – | Closed |
| [d1.1](https://dbggr.dev/models/d1-1/) | $0.02 | – | Closed |
| [d1-2B](https://dbggr.dev/models/d1-2b/) | Self-host | – | Open |
| [d1-omni-2B](https://dbggr.dev/models/d1-omni-2b/) | Self-host | – | Open |
| [Drex 1.5](https://dbggr.dev/models/drex-v1-5/) | $0.05 | – | Open |
| [Drex 2.0](https://dbggr.dev/models/drex-v2-0/) | $0.06 | – | Open |
| [Kev-0.8B](https://dbggr.dev/models/kev-0-8b/) | Self-host | – | Open |
| [Kev-4B](https://dbggr.dev/models/kev-4b/) | Self-host | – | Open |
| [Koa Decisions](https://dbggr.dev/models/koa-decisions/) | Self-host | – | Closed |
| [Strands Decider 12B](https://dbggr.dev/models/strands-decider-12b/) | Self-host | – | Open |
| [Strands Decider 2B](https://dbggr.dev/models/strands-decider-2b/) | Self-host | – | Open |
| [Strands Decider E2B](https://dbggr.dev/models/strands-decider-e2b/) | Self-host | – | Open |
| [Strands Decider E4B](https://dbggr.dev/models/strands-decider-e4b/) | Self-host | – | Open |

## FAQ

### How much does iota-decide-4b cost?

iota-decide-4b has no hosted, per-token price: you download it and run it yourself, so the cost is your own compute.

### Is iota-decide-4b open weight?

Yes. Macrocosmos publishes the weights under Apache 2.0, so you can run and fine-tune it yourself.

### How fast is iota-decide-4b?

Macrocosmos doesn't publish a latency figure. JevBench gives 0.22 seconds per decision, its estimate for self-hosting.

### How does iota-decide-4b compare with Jev?

On JevBench's Capability Score (board v1.7.46), iota-decide-4b scores 74.0 against Jev's 77.1. Jev costs $0.042 per million input tokens; iota-decide-4b is self-host only. JevBench is a one-person project that uses Jev as its reference, which favours cheap hosted models.