MiMo-V2.6-Flash — VRAM, speed & local setup
Written by Jakub Rusinowski · Last updated
The smaller MiMo-V2.6: 309B parameters (310.8B in the published tensors) with 15B active per token, 256 experts with 8 routed, 48 layers of which 39 use a 128-token sliding window and 9 use full attention. Text, image, video and audio in; 1M-token context; MIT. Every expert must be resident, about 188 GB at Q4_K_M, so it is a 256 GB unified-memory or multi-GPU model. Xiaomi publishes two checkpoints of the same size: -RL, and -MOPD, which it recommends for agents.
MiMo-V2.6-Flash needs about 188 GB of VRAM at Q4_K_M — quantized weights plus framework overhead, before any KV cache. On Apple Silicon that figure comes out of unified memory.
VRAM and speed by quantization
Quoted against NVIDIA RTX 4090 (24 GB). Includes the KV cache at 8K context, so it reads higher than the headline figure.
| Quant | Memory | VRAM | Speed (est.) | Fit |
|---|---|---|---|---|
| Q2_K 2.63 bpw | 103.2 GB | — | Too big | |
| Q3_K_M 3.41 bpw | 133.5 GB | — | Too big | |
| Q4_K_M 4.83 bpw | 188.6 GB | — | Too big | |
| Q5_K_M 5.67 bpw | 221.3 GB | — | Too big | |
| Q6_K 6.56 bpw | 255.8 GB | — | Too big | |
| Q8_0 8.50 bpw | 331.2 GB | — | Too big | |
| F16 16.00 bpw | 622.5 GB | — | Too big |
Black marker = usable memory on the NVIDIA RTX 4090 (24 GB). Estimates from the memory-bandwidth roofline on the methodology page. MiMo-V2.6-Flash VRAM calculator →
Get MiMo-V2.6-Flash running
The cheapest catalogued GPU that runs MiMo-V2.6-Flash is the Apple M3 Ultra (512 GB).
As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.
How to run MiMo-V2.6-Flash
No Ollama library entry. Xiaomi's documented serving routes are SGLang and vLLM; a ggml-org GGUF exists for llama.cpp.
Specifications
Corroborated — Two or more independent sources agree on these figures, but the model card itself was not retrieved. Treat the numbers as good rather than confirmed. Still unconfirmed: active parameters (15B: model card only).
- Parameters
- 309 Billion (15B active)
- Context window
- 1,048,576
- Architecture
- Sparse MoE (256 experts, 8 active), hybrid sliding-window attention; vision + audio encoders
- Provider
- Xiaomi
- Licence
- MIT
- Availability
- Weights downloadable
- Practical deployment
- Workstation (large unified memory or pro GPU)
- Specified at
- Q4_K_M
- System RAM
- 256 GB
- Record updated
- 2026-10-15
Commercial use permitted. No usage restrictions beyond attribution.
Quality and use cases
Scores as published by the model’s authors or an independent evaluator — quality, not throughput, and not measured by us.
Other MiMo-V2.6 sizes
MiMo-V2.6-Flash — frequently asked questions
How much VRAM does MiMo-V2.6-Flash need?
About 188 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-Flash run on an RTX 4090 (24 GB)?
No. MiMo-V2.6-Flash needs about 188 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 MiMo-V2.6-Flash locally?
No Ollama library entry. Xiaomi's documented serving routes are SGLang and vLLM; a ggml-org GGUF exists for llama.cpp. 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.