JevK5 4B — VRAM & /v1/systemone setup
Autor: Jakub Rusinowski · Ostatnia aktualizacja:
Model decyzyjny 4B na Qwen3.5-4B-Base z serwerem w stylu TypeSafe; tylko angielski, a dane wejściowe powyżej 16 384 tokenów są odrzucane, a nie przycinane.
JevK5 4B potrzebuje około 4 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 JevK5 4B
Served by jevk5-serve (default port 8090). This model does not run in Ollama.
- Question types
- choice noul (yes / no) score
- Inputs
- text
- Serve with
jevk5-serve :8090- Endpoint
/v1/systemone
http://localhost:8090/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 12B · Winnow E4B · Decider 2B · Decider 4B · Decider 35B-A3B (NVFP4) · 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 16,384-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.
| Kwant. | Pamięć | VRAM | Dopasowanie |
|---|---|---|---|
| BF16 Publisher build · 9 GB file | 11.7 GB | Mieści się | |
| Q4_K_M 4.83 bpw · modelled quant | 5.6 GB | Mieści się | |
| Q6_K 6.56 bpw · modelled quant | 6.6 GB | Mieści się | |
| Q8_0 8.50 bpw · modelled quant | 7.7 GB | Mieści się |
Published file size: BF16 9 GB. A download size from the model publisher — not a VRAM requirement.
English only. Inputs over 16,384 tokens refused, not cut. Server: jevk5-serve --model alibiserikbay/JevK5 --port 8090. GGUF Q8_0/Q4_K_M in JevK5-GGUF.
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)
- 0.0268
- Median compute
- 22 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. Jeszcze niepotwierdzone: weightsGbByQuant.
- Parametry
- 4.66B
- Okno kontekstu
- 16K (prompt limit)
- Architektura
- Fine-tune of Qwen/Qwen3.5-4B-Base
- Dostawca
- alibiserikbay
- Licencja
- Apache-2.0
- Practical deployment
- Edge device (phone, SBC)
- Określono przy
- Q4_K_M
- RAM systemowy
- 8 GB
- Rekord zaktualizowany
- 2026-09-30
Commercial use permitted. No usage restrictions beyond attribution.
JevK5 4B — najczęściej zadawane pytania
What is JevK5 4B?
JevK5 4B 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 JevK5 4B locally?
JevK5 4B does not run in Ollama. Served by jevk5-serve (default port 8090). This model does not run in Ollama. See the setup guide for servers other than Ollama.
How much memory does JevK5 4B need?
About 4 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 JevK5 4B?
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.