Mimo 2.6 VRAM requirements
Memory needed to run Mimo 2.6 at every published size and quant, with an 8k context. Each figure is weights plus KV cache plus runtime buffers, from the same memory model as the VRAM calculator.
Total memory by size and quant
GB at an 8k context. Bold is the Q4_K_M column, the usual starting point.
| Size | Q8_0 | Q6_K | Q5_K_M | Q4_K_M | Q3_K_M |
|---|---|---|---|---|---|
| 9B | 11 | 9.3 | 8.2 | 7.0 | 5.9 |
| 309B · 15B active | 311 | 253 | 214 | 176 | 137 |
| 1020B · 42B active | 1022 | 831 | 703 | 576 | 448 |
KV cache by context length
GB the context alone adds on top of the weights. Add this to a weights figure to size a longer session.
| Size | Weights at Q4_K_M | 4k ctx | 16k ctx | 32k ctx | 128k ctx |
|---|---|---|---|---|---|
| 9B | 5.1 | 0.1 | 0.4 | 0.8 | 3.0 |
| 309B · 15B active | 174 | 0.1 | 0.4 | 0.8 | 3.0 |
| 1020B · 42B active | 574 | 0.2 | 0.9 | 1.7 | 6.8 |
What each size fits on at Q4_K_M
Hardware whose memory holds the model with headroom, smallest pool first. Fits means under 85% of the pool at an 8k context. A Mac's pool is what macOS lets the GPU use - two thirds of its memory up to 32 GB, three quarters from 36 GB - not the whole of it.
- 9Bneeds about 7.0 GB
Smallest: AMD RX 6700 (10 GB), NVIDIA P102-100 (10 GB), NVIDIA RTX 3080 10GB (10 GB), NVIDIA GTX 1080 Ti (11 GB), and 106 more.
On a Mac: 16 GB or more, with macOS's default GPU limit.
- 309B · 15B activeneeds about 176 GB
Smallest: AMD Instinct MI325X (256 GB), NVIDIA B300 288GB (288 GB), NVIDIA Rubin 288GB (288 GB).
On a Mac: 512 GB or more, with macOS's default GPU limit.
- 1020B · 42B activeneeds about 576 GB
Does not fit any single GPU or Mac on llamaperf at Q4_K_M. It needs a multi-GPU rig, a smaller quant, or CPU offloading.
Frequently asked
How much VRAM does Mimo 2.6 need?
From about 7.0 GB for the 9B model to about 576 GB for the 1020B · 42B active model, at Q4_K_M with an 8k context and including the KV cache and runtime buffers. Q8 needs more and Q3 less; the table above lists every size and rung.
Can I run Mimo 2.6 on a 16GB GPU?
Yes. The 9B model needs about 7.0 GB at Q4_K_M with an 8k context, which fits a 16 GB card with headroom. Larger sizes need a smaller quant or a bigger card.
Can I run Mimo 2.6 on a 24GB GPU such as an RTX 3090 or 4090?
Yes. The 9B model needs about 7.0 GB at Q4_K_M with an 8k context, which fits a 24 GB card with headroom. Larger sizes need a smaller quant or more memory.
How are these numbers calculated?
Weights at the quant's bits per weight, plus a KV cache sized from the model's attention design for the chosen context, plus compute buffers and a fixed runtime allowance. It is the same memory model the VRAM calculator uses. A family whose attention profile is not on file is sized as plain grouped-query attention, which errs towards needing more memory.