MiMo-V2.6 Distill 9B — 显存、速度与本地部署
作者： Jakub Rusinowski · 最后更新：
Xiaomi's MiMo-V2.6-Distill-Qwen-9B. NOT a MiMo-V2.6 model scaled down: this is Qwen3.5-9B fine-tuned by Xiaomi on data generated by MiMo-V2.6, for coding and tool use. Dense, 8.95B in the language model plus a vision tower, 32 layers with 8 full-attention layers, 262,144-token context, MIT. It is the member of the MiMo-V2.6 release that runs on a laptop: about 6 GB at Q4_K_M. Xiaomi reports SWE-bench Verified 61.1 against 60.0 for the Qwen3.5-9B it started from.
MiMo-V2.6 Distill 9B 在 Q4_K_M 下约需 6 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 | 4 GB | ~158 tok/s | 可运行 | |
| Q3_K_M 3.41 bpw | 4.9 GB | ~134 tok/s | 可运行 | |
| Q4_K_M 4.83 bpw | 6.5 GB | ~104 tok/s | 可运行 | |
| Q5_K_M 5.67 bpw | 7.4 GB | ~92 tok/s | 可运行 | |
| Q6_K 6.56 bpw | 8.4 GB | ~82 tok/s | 可运行 | |
| Q8_0 8.50 bpw | 10.6 GB | ~67 tok/s | 可运行 | |
| F16 16.00 bpw | 19 GB | ~38 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. MiMo-V2.6 Distill 9B 显存计算器 →
运行 MiMo-V2.6 Distill 9B
目录中能运行 MiMo-V2.6 Distill 9B 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 MiMo-V2.6 Distill 9B
No Ollama library entry. GGUF builds from ggml-org and others run in llama.cpp and LM Studio.
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
- 8.95 Billion (+ vision tower)
- 上下文窗口
- 262,144
- 架构
- Qwen3.5-9B hybrid attention (distilled), vision via projector
- 提供商
- Xiaomi
- 许可证
- MIT
- Availability
- Weights downloadable
- Practical deployment
- Laptop
- 规格量化
- Q4_K_M
- Vision projector
- +0.6 GB when you send images (not included above)
- 系统内存
- 16 GB
- 记录更新于
- 2026-10-15
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 |
|---|---|---|
| SWE-bench Verified (avg@3) | 61.1 % | 厂商声称 · Xiaomi model card |
MiMo-V2.6 的其他尺寸
MiMo-V2.6 Distill 9B — 常见问题
How much VRAM does MiMo-V2.6 Distill 9B need?
About 6 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 MiMo-V2.6 Distill 9B run on an RTX 4090 (24 GB)?
Yes. MiMo-V2.6 Distill 9B needs about 6 GB at Q4_K_M, inside a 24 GB card, at an estimated 104 tokens/sec.
How do I run MiMo-V2.6 Distill 9B locally?
No Ollama library entry. GGUF builds from ggml-org and others run in llama.cpp and LM Studio. Running the published tag would send your prompts to a hosted GPU rather than your own machine.
What other sizes does MiMo-V2.6 come in?
MiMo-V2.6-Pro (619 GB), MiMo-V2.6-Flash (188 GB), MiMo-V2.6 Distill 9B (6 GB). Every size shares the family's training and licence; the larger ones score higher and need proportionally more memory.