RunsOnMy ModelsGPUs & MacsBy VRAMBest GPUCan I run…?OllamaStart hereAPI pricesVRAM calculatorNew

Can MiMo V2.6 Distill Qwen 9B run on the RX 9070?

Yes. At 8K context the best fit is Q8_0, using about 10.0 GB of the 15.2 GB usable on the RX 9070. Estimated speed ceiling: ~67 tokens/sec.

+ 0.9 GB with image input. The figures on this page are for text only. With image input enabled, the vision projector (mmproj) file loads alongside the model: Q8_0 at 8K context then needs about 10.9 GB (still fits). llama.cpp's -hf downloads and loads it automatically unless you add --no-mmproj. Calculator with image input on.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K) •4.4 GB Fits4.5 GB Fits5.3 GB Fits8.3 GB Fits176
3-bit (Q3_K_M) •5.2 GB Fits5.3 GB Fits6.0 GB Fits9.0 GB Fits143
4-bit (Q4_K_M) •6.4 GB Fits6.6 GB Fits7.3 GB Fits10.3 GB Fits110
5-bit (Q5_K_M) •7.4 GB Fits7.5 GB Fits8.3 GB Fits11.3 GB Fits93
6-bit (Q6_K) •8.3 GB Fits8.4 GB Fits9.1 GB Fits12.1 GB Fits82
8-bit (Q8_0) •9.9 GB Fits10.0 GB Fits10.8 GB Fits13.8 GB Tight67
16-bit (F16/BF16) •17.7 GB No17.8 GB No18.6 GB No21.6 GB No—

• real GGUF file size from bartowski/MiMo-V2.6-Distill-Qwen-9B-GGUF. Speed is a bandwidth ceiling (640 GB/s), not a benchmark. Methodology.

What fits instead

"Runs" and "fits" mean the whole model in GPU memory at 8K context (4-bit or better for the model pick). Prices are US launch MSRPs, not today's street prices. "Popular" means the 60 most-downloaded models we track.

More

MiMo V2.6 Distill Qwen 9B on every GPU and Mac · Every model that runs on the RX 9070 · Other models that fit 16 GB VRAM · Try other settings in the calculator

Guides: Best GPU for local LLMs by budget · Can I run gpt-oss, Llama 70B or Qwen3? · Mac vs PC for local LLMs

Data: Hugging Face Hub (XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B), AMD specs. Model data last checked 2026-11-18; refreshed hourly.