证据: 基准测试结果由厂商自行报告
Step 5 Preview 600B-A27B — 显存、速度与本地部署
作者： Jakub Rusinowski · 最后更新：
StepFun 的 600B 参数 MoE，每个 token 激活 27B，上下文最多 100 万 token，支持文本、图像和视频输入。共 92 层，其中 23 层为全注意力，69 层为 512 token 滑动窗口。自 2026 年 10 月 15 日起提供 FP8、BF16 和 NVFP4 权重。属于服务器级模型：StepFun 的示例在多 GPU 节点上运行。
Step 5 Preview 600B-A27B 在 Q4_K_M 下约需 366 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)。包含 8K 上下文的 KV 缓存，因此数值高于上方的主数字。
| 量化 | 显存 | 显存 | 速度（估算） | 适配 |
|---|---|---|---|---|
| Q2_K 2.63 bpw | 200.3 GB | — | 放不下 | |
| Q3_K_M 3.41 bpw | 259.2 GB | — | 放不下 | |
| Q4_K_M 4.83 bpw | 366.4 GB | — | 放不下 | |
| Q5_K_M 5.67 bpw | 429.9 GB | — | 放不下 | |
| Q6_K 6.56 bpw | 497.1 GB | — | 放不下 | |
| Q8_0 8.50 bpw | 643.7 GB | — | 放不下 | |
| F16 16.00 bpw | 1210.2 GB | — | 放不下 |
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. Step 5 Preview 600B-A27B 显存计算器 →
运行 Step 5 Preview 600B-A27B
Step 5 Preview 600B-A27B is not practical on a single consumer GPU: it needs about 365.6 GB at Q4_K_M, more than any single device in our catalogue holds with headroom. How multi-GPU inference works, or rent a multi-GPU server by the hour:
如何运行 Step 5 Preview 600B-A27B
No Ollama tag and no official GGUF. StepFun documents vLLM and SGLang serving.
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
- 600 Billion (27B active)
- 上下文窗口
- 1,048,576
- 架构
- Mixture-of-Experts (352 routed + 1 shared, 8 active), GQA with 3:1 sliding-window to full attention
- 提供商
- StepFun
- 许可证
- StepFun Model License 1.0
- Practical deployment
- Multi-GPU server
- 规格量化
- Q4_K_M
- 系统内存
- 512 GB
- 记录更新于
- 2026-11-03
Weights are downloadable and commercial use is permitted, subject to the licence’s acceptable-use terms.
Above 100M monthly active users or $20M monthly revenue a product must display "Powered by StepFun AI"; device makers, and model-as-a-service operators above $20M revenue in any 12 months, need a separate commercial licence.
限制与注意事项
- A preview release by name; StepFun may change it.
- No official GGUF; the published formats are FP8, BF16 and NVFP4.
- Benchmarks on the card are vendor-reported.
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。
StepFun Step 的其他尺寸
Step 5 Preview 600B-A27B — 常见问题
How much VRAM does Step 5 Preview 600B-A27B need?
About 366 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 Step 5 Preview 600B-A27B run on an RTX 4090 (24 GB)?
No. Step 5 Preview 600B-A27B needs about 366 GB at Q4_K_M, more than a single RTX 4090's 24 GB. It needs a larger card, several GPUs, or Apple Silicon with enough unified memory — or it runs with part of the weights offloaded to system RAM, which is much slower.
How do I run Step 5 Preview 600B-A27B locally?
No Ollama tag and no official GGUF. StepFun documents vLLM and SGLang serving. Running the published tag would send your prompts to a hosted GPU rather than your own machine.
What other sizes does StepFun Step come in?
Step 3.7 Flash 198B-A11B (112 GB), Step 5 Preview 600B-A27B (366 GB). Every size shares the family's training and licence; the larger ones score higher and need proportionally more memory.