VibeThinker 1.5B — 显存、速度与本地部署
作者: Jakub Rusinowski · 最后更新:
The original VibeThinker, fine-tuned from Qwen2.5-Math-1.5B. Reports 80.3 / 74.4 / 50.4 on AIME24, AIME25 and HMMT25 — above DeepSeek R1 on those three at roughly 1/400th the parameter count. Under 2 GB at Q4_K_M, so it runs on a phone.
VibeThinker 1.5B 在 Q4_K_M 下约需 2 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。
按量化级别的显存与速度
计算基准:NVIDIA RTX 4090 (24 GB)。仅含权重与开销:该模型架构未公开,因此未计入 KV 缓存。
| 量化 | 显存 | 显存 | 速度(估算) | 适配 |
|---|---|---|---|---|
| Q2_K 2.63 bpw | 1.3 GB | ~298 tok/s | 可运行 | |
| Q3_K_M 3.41 bpw | 1.5 GB | ~281 tok/s | 可运行 | |
| Q4_K_M 4.83 bpw | 1.7 GB | ~255 tok/s | 可运行 | |
| Q5_K_M 5.67 bpw | 1.9 GB | ~242 tok/s | 可运行 | |
| Q6_K 6.56 bpw | 2.1 GB | ~229 tok/s | 可运行 | |
| Q8_0 8.50 bpw | 2.4 GB | ~206 tok/s | 可运行 | |
| F16 16.00 bpw | 3.9 GB | ~148 tok/s | 可运行 |
黑色标记 = NVIDIA RTX 4090 (24 GB) 上的可用显存。 估算来自内存带宽屋顶线模型,详见 方法说明页. VibeThinker 1.5B 显存计算器 →
运行 VibeThinker 1.5B
目录中能运行 VibeThinker 1.5B 的最便宜 GPU 是 Intel Arc B570 (10 GB).
或在 Vast.ai 比较,低至 $0.35/小时 (typical low · varies)
作为亚马逊联盟成员,我们从符合条件的购买中获得收入。云 GPU 链接为推荐链接——我们可能获得佣金,您无需额外付费。
如何运行 VibeThinker 1.5B
安装 Ollama,然后运行:
ollama run vibethinker规格
Verified — Checked against the primary source — the model card or the vendor spec page — and corroborated by a second independent source.
- 参数量
- 1.54 Billion
- 上下文窗口
- 131,072
- 架构
- Dense Transformer (Qwen2.5-Math-1.5B base)
- 提供商
- WeiboAI
- 许可证
- MIT
- Practical deployment
- Edge device (phone, SBC)
- 规格量化
- Q4_K_M
- 系统内存
- 4 GB
- 记录更新于
- 2026-09-06
Commercial use permitted. No usage restrictions beyond attribution.
质量与使用场景
评分由模型作者或独立评测方发布——衡量质量而非吞吐量,并非我们实测。
| 基准 | 分数 | 来源 |
|---|---|---|
| AIME 2024 | 80.3 / 100 % | 厂商声称 · https://github.com/WeiboAI/VibeThinker |
| AIME 2025 | 74.4 / 100 % | 厂商声称 · https://github.com/WeiboAI/VibeThinker |
我的 GPU 能运行 VibeThinker 1.5B 吗?
VibeThinker 的其他尺寸
VibeThinker 1.5B — 常见问题
How much VRAM does VibeThinker 1.5B need?
About 2 GB at Q4_K_M — quantized weights plus framework overhead, before any KV cache. The cache grows with context length and is added on top; the table above folds it in. Apple Silicon counts unified memory toward the same figure.
Does VibeThinker 1.5B run on an RTX 4090 (24 GB)?
Yes. VibeThinker 1.5B needs about 2 GB at Q4_K_M, inside a 24 GB card, at an estimated 255 tokens/sec.
How do I run VibeThinker 1.5B locally?
Install Ollama and run `ollama run vibethinker`. That pulls the weights and starts a local OpenAI-compatible endpoint; after the download nothing leaves the machine.
What other sizes does VibeThinker come in?
VibeThinker 3B (3 GB), VibeThinker 1.5B (2 GB). Every size shares the family's training and licence; the larger ones score higher and need proportionally more memory.