Tev1 4B — VRAM & /v1/systemone setup
作者： Jakub Rusinowski · 最后更新：
Together AI 的实验性 4B 决策模型，是对 Qwen3.5-4B 的监督微调。在 Ollama 中名为 tev1；输入建议保持在约 2,000 个 token。
Tev1 4B 在 Q4_K_M 下约需 4 GB 显存——量化权重加框架开销，不含 KV 缓存。在 Apple Silicon 上，这部分来自统一内存。
Call Tev1 4B
Pull it with Ollama 0.35 or newer, then POST to /v1/systemone. Do not use ollama chat commands — this is not a chat model.
- Question types
- choice noul (yes / no) score
- Inputs
- text
- Max candidates per question
- 26
- Serve with
ollama pull tev1- Endpoint
/v1/systemone
ollama pull tev1curl http://localhost:11434/v1/systemone \
-H 'Content-Type: application/json' \
-d '{
"model": "tev1",
"state": {
"ticket": "I was charged twice. Please refund the extra payment."
},
"questions": {
"team": {
"type": "choice",
"instructions": "Which team should handle this ticket?",
"criteria": {
"billing": "Payments and refunds",
"technical": "Bugs and integrations",
"other": "None of the above"
}
}
}
}'Build a request for this model Decision models guide
Other decision models: Nimble 9B · Tev1 0.8B · Winnow 12B · 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.
| 量化 | 显存 | 显存 | 适配 |
|---|---|---|---|
| Ollama build Publisher build · 4.5 GB file | 6.3 GB | 可运行 | |
| Q4_K_M 4.83 bpw · modelled quant | 4.6 GB | 可运行 | |
| Q6_K 6.56 bpw · modelled quant | 5.6 GB | 可运行 | |
| Q8_0 8.50 bpw · modelled quant | 6.7 GB | 可运行 |
Published file size: Ollama build 4.5 GB. A download size from the model publisher — not a VRAM requirement.
Model card: a Jev-inspired experiment, not a non-autoregressive Jev runtime; keeps Qwen's LM head. Ollama card: keep inputs ~2,000 tokens; not for high-stakes decisions without review.
How it was scored
Two different suites on two different scales. Never compare the numbers across the two cards.
Author's public benchmark
Bespoke Labs public benchmarks (13 datasets, 3,880 decisions)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)
- 0.104
- Median compute
- 35.8 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.
规格
Verified — Checked against the primary source — the model card or the vendor spec page — and corroborated by a second independent source. 尚未确认： license.
- 参数量
- 4.66B
- 上下文窗口
- Not published
- 架构
- Fine-tune of Qwen/Qwen3.5-4B
- 提供商
- Together AI
- 许可证
- Not stated on the model card
- Practical deployment
- Edge device (phone, SBC)
- 规格量化
- Q4_K_M
- 系统内存
- 8 GB
- 记录更新于
- 2026-09-30
Tev1 (experimental) 的其他尺寸
Tev1 4B — 常见问题
What is Tev1 4B?
Tev1 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 Tev1 4B locally?
Install Ollama 0.35 or newer, run `ollama pull tev1`, then POST your state and questions to http://localhost:11434/v1/systemone. It is called through the API, not a chat session.
How much memory does Tev1 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 Tev1 4B?
It has separate published scores on different suites — the community Decision Index 0.2.1 and the benchmarks listed on this page. They are not comparable with each other, and none is a calibration guarantee.