AI Hashrate · Ryzen AI Max+ 395 128GB
Which LLM should you run on the Ryzen AI Max+ 395 128GB?
96 GB · 215 GB/s · 120 W
Every number below comes from the same engine behind the wizard: VRAM fit per quantisation, decode speed from memory bandwidth, and a command you can paste. Nothing is scraped or invented.
The short answer
Qwen3.6-35B-A3B — about 66.5 tok/s decode
Also fits
| Model | Q4 VRAM | Est. tok/s |
|---|---|---|
| gemma-4-26B-A4B-it | 15.4 GB | 52.5 |
| Qwen3-Next-80B-A3B-Instruct | 47.3 GB | 66.5 |
| Qwen3.5-35B-A3B | 20.6 GB | 66.5 |
| gpt-oss-20b | 13.2 GB | 55.4 |
| Ornith-1.0-35B | 20.8 GB | 66.5 |
| Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16 | 18.2 GB | 66.5 |
| Qwen3-30B-A3B-Instruct-2507 | 18.8 GB | 66.5 |
Run it
llama-server \
-hf <GGUF_REPO>:Q4_K_M \
-c 8192 \
-ngl 99 \
--host 127.0.0.1 --port 8080These figures are modelled estimates from hardware specs and public reports, not benchmarks measured on this card. The wizard shows where every number comes from.