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

Can Llama Guard 4 12B run on the Ryzen AI Max+ 395 128GB?

Yes. At 8K context the best fit is F16, using about 24.6 GB of the 109 GB usable on the Ryzen AI Max+ 395 128GB. Estimated speed ceiling: ~11 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K)5.7 GB Fits6.5 GB Fits11.0 GB Fits29.0 GB Fits57
3-bit (Q3_K_M)7.0 GB Fits7.7 GB Fits12.2 GB Fits30.2 GB Fits44
4-bit (Q4_K_M)8.4 GB Fits9.1 GB Fits13.6 GB Fits31.6 GB Fits35
5-bit (Q5_K_M)9.5 GB Fits10.2 GB Fits14.7 GB Fits32.7 GB Fits30
6-bit (Q6_K)10.7 GB Fits11.5 GB Fits16.0 GB Fits34.0 GB Fits26
8-bit (Q8_0)13.4 GB Fits14.2 GB Fits18.7 GB Fits36.7 GB Fits20
16-bit (F16/BF16)23.9 GB Fits24.6 GB Fits29.1 GB Fits47.1 GB Fits11

• real GGUF file size. Speed is a bandwidth ceiling (256 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

Llama Guard 4 12B on every GPU and Mac · Every model that runs on the Ryzen AI Max+ 395 128GB · Other models that fit 64 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-llama/Llama-Guard-4-12B), AMD specs. Model data last checked 2026-11-18; refreshed hourly.