Winnow 12B — VRAM & /v1/systemone setup
Autor: Jakub Rusinowski · Ostatnia aktualizacja:
Model decyzyjny 12B od EldanRing na Gemma 4 12B, wydawany jako GGUF i obsługiwany przez serwer winnow-inference oparty na llama.cpp, który obsługuje też czat i obraz.
Winnow 12B potrzebuje około 8 GB VRAM przy Q4_K_M — skwantyzowane wagi plus narzut frameworka, bez pamięci podręcznej KV. Na Apple Silicon ta wartość pochodzi z pamięci zunifikowanej.
Call Winnow 12B
Served by winnow-inference (default port 8091). This model does not run in Ollama.
- Question types
- choice noul (yes / no) score
- Inputs
- text image
- Serve with
winnow-inference :8091- Endpoint
/v1/systemone
http://localhost:8091/v1/systemone
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 E4B · Decider 2B · Decider 4B · Decider 35B-A3B (NVFP4) · JevK5 4B · Intern-Decision 4B · AutoJev 27B · Laya · Clef 27B · Clef-Flash 9B · Rune 26B-A4B v3 · OpenDecider-nano · OpenDecider-small · OpenDecider-small MLX 4-bit · Bosun v3.1 0.6B · Bosun v3.1 1.7B · d1-3B · d1-omni-600M · THX-01 322M
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. Image tokens are not modelled: each image adds to the prompt, so a request with images needs more memory than these rows.
| Kwant. | Pamięć | VRAM | Dopasowanie |
|---|---|---|---|
| BF16 Publisher build · 23.83 GB file | 25.9 GB | Częściowo w RAM | |
| Q4_K_M 4.83 bpw · modelled quant | 9.3 GB | Mieści się | |
| Q6_K 6.56 bpw · modelled quant | 11.9 GB | Mieści się | |
| Q8_0 8.50 bpw · modelled quant | 14.8 GB | Mieści się |
Published file size: Q8_0 12.67 GB · BF16 23.83 GB. A download size from the model publisher — not a VRAM requirement.
Runs in the Winnow llama.cpp-based server (default port 8091): /v1/systemone + /v1/chat/completions + vision. Tested: RTX 5070 Ti 16 GB (Q8_0, 64K ctx); Apple Silicon 24 GB+. Not usable on Ollama's /v1/systemone.
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 0.2.1Community Decision Index (not by the model's authors)- ECE (lower is better)
- 0.1679
- Median compute
- 72.5 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.
Specyfikacja
Verified — Checked against the primary source — the model card or the vendor spec page — and corroborated by a second independent source.
- Parametry
- 11.96B
- Okno kontekstu
- Not published
- Architektura
- Fine-tune of google/gemma-4-12B
- Dostawca
- EldanRing
- Licencja
- Apache-2.0
- Practical deployment
- Laptop
- Określono przy
- Q4_K_M
- RAM systemowy
- 18 GB
- Rekord zaktualizowany
- 2026-09-30
Commercial use permitted. No usage restrictions beyond attribution.
Inne rozmiary Winnow
Winnow 12B — najczęściej zadawane pytania
What is Winnow 12B?
Winnow 12B 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 Winnow 12B locally?
Winnow 12B does not run in Ollama. Served by winnow-inference (default port 8091). This model does not run in Ollama. See the setup guide for servers other than Ollama.
How much memory does Winnow 12B need?
About 8 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 Winnow 12B?
Its published score is on the community Decision Index 0.2.1, which its authors did not build. It is not a calibration guarantee: test on your own examples.