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

Can Muse Spark Open 816B A42B run on the RX 9070?

No. Even at 2-bit with 8K context, Muse Spark Open 816B A42B needs about 285 GB, more than the 15.2 GB usable on the RX 9070.

Even with llama.cpp CPU offload (-ngl, --n-cpu-moe) and 128 GB of system RAM, this model does not fit at 2-bit, or the card cannot hold a useful share of it. See the offload method.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K) •285 GB No285 GB No286 GB No292 GB No—
3-bit (Q3_K_M)376 GB No376 GB No377 GB No383 GB No—
4-bit (Q4_K_M)469 GB No470 GB No471 GB No477 GB No—
5-bit (Q5_K_M)547 GB No547 GB No549 GB No555 GB No—
6-bit (Q6_K)629 GB No629 GB No631 GB No637 GB No—
8-bit (Q8_0) •813 GB No813 GB No815 GB No821 GB No—
16-bit (F16/BF16) •1529 GB No1529 GB No1531 GB No1537 GB No—

• real GGUF file size from ggml-org/Muse-Spark-Open-816B-A42B-GGUF. Speed is a bandwidth ceiling (640 GB/s), not a benchmark. Methodology.

Hardware that does fit it

Mac M3 Ultra 512GB

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

Muse Spark Open 816B A42B 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 (meta-models/Muse-Spark-Open-816B-A42B), AMD specs. Model data last checked 2026-11-17; refreshed hourly.