Can MiMo V2.6 Distill Qwen 9B run on the RTX 5070?
Yes. At 8K context the best fit is Q8_0, using about 10.0 GB of the 11.4 GB usable on the RTX 5070. Estimated speed ceiling: ~70 tokens/sec.
Memory by quant and context
| Quant | 4K ctx | 8K ctx | 32K ctx | 128K ctx | Max tok/s (est., 8K) |
|---|---|---|---|---|---|
| 2-bit (Q2_K) • | 4.4 GB Fits | 4.5 GB Fits | 5.3 GB Fits | 8.3 GB Fits | 184 |
| 3-bit (Q3_K_M) • | 5.2 GB Fits | 5.3 GB Fits | 6.0 GB Fits | 9.0 GB Fits | 150 |
| 4-bit (Q4_K_M) • | 6.4 GB Fits | 6.6 GB Fits | 7.3 GB Fits | 10.3 GB Tight | 115 |
| 5-bit (Q5_K_M) • | 7.4 GB Fits | 7.5 GB Fits | 8.3 GB Fits | 11.3 GB Tight | 98 |
| 6-bit (Q6_K) • | 8.3 GB Fits | 8.4 GB Fits | 9.1 GB Fits | 12.1 GB No | 86 |
| 8-bit (Q8_0) • | 9.9 GB Fits | 10.0 GB Fits | 10.8 GB Tight | 13.8 GB No | 70 |
| 16-bit (F16/BF16) • | 17.7 GB No | 17.8 GB No | 18.6 GB No | 21.6 GB No | — |
• real GGUF file size from bartowski/MiMo-V2.6-Distill-Qwen-9B-GGUF. Speed is a bandwidth ceiling (672 GB/s), not a benchmark. Methodology.
More
MiMo V2.6 Distill Qwen 9B on every GPU and Mac · Every model that runs on the RTX 5070 · Other models that fit 12 GB VRAM · Try other settings in the calculator
Data: Hugging Face Hub (XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B), NVIDIA specs. Data as of 2026-11-17.