Kimi K3 2.8T — 显存、速度与本地部署
作者： Jakub Rusinowski · 最后更新：
The full 2.8-trillion-parameter Kimi K3 MoE, activating 104B parameters per token by selecting 16 of 896 experts. Moonshot's largest and most capable model, positioned above Kimi K2.6 on agentic coding and long-horizon reasoning at release. Native text + vision with a 1M-token context. Weights went public on 26–27 July 2026 under the bespoke Kimi K3 License — open-weight, but not an OSI-approved open-source license, so check the commercial threshold before deploying. Self-hosting requires ~1.4 TB of memory at Q4, so in practice this is an API model — as is every Kimi K2.x release, which are all 1T-class MoE models despite their 32B active-parameter figure.
Kimi K3 2.8T 在 Q4_K_M 下约需 1691 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 | 921.3 GB | — | 放不下 | |
| Q3_K_M 3.41 bpw | 1194.3 GB | — | 放不下 | |
| Q4_K_M 4.83 bpw | 1691.3 GB | — | 放不下 | |
| Q5_K_M 5.67 bpw | 1985.3 GB | — | 放不下 | |
| Q6_K 6.56 bpw | 2296.8 GB | — | 放不下 | |
| Q8_0 8.50 bpw | 2975.8 GB | — | 放不下 | |
| F16 16.00 bpw | 5600.8 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. Kimi K3 2.8T 显存计算器 →
运行 Kimi K3 2.8T
Kimi K3 2.8T is not practical on a single consumer GPU: it needs about 1691.3 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 Kimi K3 2.8T
No local Ollama tag. Ollama lists kimi-k3 only as a cloud-hosted ':cloud' tag, which runs on Ollama's servers, not your machine.
规格
Preview — The model is released, but these specs are thin or rest on a single source. Individual fields may be wrong.
Preview — The model is released, but these specs are thin or rest on a single source. Individual fields may be wrong.
- 参数量
- 2.8 Trillion (104B active)
- 上下文窗口
- 1,000,000
- 架构
- Mixture-of-Experts (896 experts, 16 active) + Vision
- 提供商
- Moonshot AI
- 许可证
- Kimi K3 License (open-weight, not OSI open-source)
- Availability
- Weights downloadable
- Practical deployment
- Private cloud / datacenter cluster
- 规格量化
- Q4_K_M
- 系统内存
- 2048 GB
- 记录更新于
- 2026-08-15
- Runs with
- Ollama: not supported source
Weights are downloadable and commercial use is permitted, subject to the licence’s acceptable-use terms.
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。
Independent evaluation — not vendor-claimed and not measured by us
| 基准 | 分数 | 来源 |
|---|---|---|
| AA Intelligence Index v4.3.2 (Max) | 44 | independent · Artificial Analysis · snapshot 2026-10-13 |
我的 GPU 能运行 Kimi K3 2.8T 吗？
Kimi K3 的其他尺寸
Kimi K3 2.8T — 常见问题
How much VRAM does Kimi K3 2.8T need?
About 1691 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 Kimi K3 2.8T run on an RTX 4090 (24 GB)?
No. Kimi K3 2.8T needs about 1691 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 Kimi K3 2.8T locally?
No local Ollama tag. Ollama lists kimi-k3 only as a cloud-hosted ':cloud' tag, which runs on Ollama's servers, not your machine. Running the published tag would send your prompts to a hosted GPU rather than your own machine.
What other sizes does Kimi K3 come in?
Kimi K3 2.8T (1691 GB), Kimi K3.1 Pro (1562 GB). Every size shares the family's training and licence; the larger ones score higher and need proportionally more memory.