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

Can Falcon 40B run on the Ryzen AI Max+ 395 128GB?

Yes. At 8K context the best fit is F16, using about 79.4 GB of the 109 GB usable on the Ryzen AI Max+ 395 128GB. Estimated speed ceiling: ~3 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K) •15.7 GB Fits16.1 GB Fits19.0 GB Fits30.2 GB Fits16
3-bit (Q3_K_M) •19.7 GB Fits20.2 GB Fits23.0 GB Fits34.2 GB Fits13
4-bit (Q4_K_M) •24.7 GB Fits25.2 GB Fits28.0 GB Fits39.3 GB Fits10
5-bit (Q5_K_M) •29.5 GB Fits30.0 GB Fits32.8 GB Fits44.1 GB Fits8
6-bit (Q6_K) •33.1 GB Fits33.6 GB Fits36.4 GB Fits47.6 GB Fits7
8-bit (Q8_0)42.4 GB Fits42.9 GB Fits45.7 GB Fits56.9 GB Fits6
16-bit (F16/BF16)78.9 GB Fits79.4 GB Fits82.2 GB Fits93.4 GB Fits3

• real GGUF file size from mradermacher/falcon-40b-i1-GGUF. 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

Falcon 40B 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 (tiiuae/falcon-40b), AMD specs. Model data last checked 2026-11-18; refreshed hourly.