RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can falcon 7b instruct run on the Ryzen AI Max+ 395 128GB?

Yes. At 8K context the best fit is F16, using about 18.4 GB of the 109 GB usable on the Ryzen AI Max+ 395 128GB. Estimated speed ceiling: ~18 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K) •6.2 GB Fits8.4 GB Fits21.7 GB Fits75.0 GB Fits69
3-bit (Q3_K_M) •6.4 GB Fits8.7 GB Fits22.0 GB Fits75.2 GB Fits64
4-bit (Q4_K_M) •7.2 GB Fits9.4 GB Fits22.7 GB Fits76.0 GB Fits54
5-bit (Q5_K_M) •7.9 GB Fits10.1 GB Fits23.4 GB Fits76.7 GB Fits46
6-bit (Q6_K) •9.0 GB Fits11.2 GB Fits24.5 GB Fits77.8 GB Fits38
8-bit (Q8_0) •9.6 GB Fits11.8 GB Fits25.1 GB Fits78.4 GB Fits35
16-bit (F16/BF16)16.2 GB Fits18.4 GB Fits31.7 GB Fits85.0 GB Fits18

• real GGUF file size from QuantFactory/falcon-7b-instruct-GGUF. Speed is a bandwidth ceiling (256 GB/s), not a benchmark. Methodology.

More

falcon 7b instruct 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

Data: Hugging Face Hub (tiiuae/falcon-7b-instruct), AMD specs. Data as of 2026-11-17.