AMD Ryzen AI Max+ 395 for local LLMs
Written by Jakub Rusinowski · Last updated
With 128 GB at 256 GB/s, the AMD Ryzen AI Max+ 395 runs 141 catalogued models at Q4_K_M with 8K context. The largest that fits is Qwen3.8-Flash-Next (~109.7 GB), and the top pick is Qwen3.8-Flash-Next at 25–51 tok/s.
"Strix Halo" SoC pairing 16 Zen 5 CPU cores with a 40-CU RDNA 3.5 iGPU (Radeon 8060S), sharing up to 128 GB of LPDDR5X-8000 memory at 256 GB/s. Up to 96 GB can be allocated to the GPU as VRAM via AMD Variable Graphics Memory (Windows) or GTT (Linux) — the figure used here. Powers AI mini-PCs like the Framework Desktop, GMKtec EVO-X2, and HP Z2 Mini G1a. ROCm support is improving but still behind CUDA.
Models that run on the AMD Ryzen AI Max+ 395
Q4_K_M, 8K context, 128 GB usable. Ranked by quality and speed.
| Model | Memory · marker = 128 GB | VRAM | Speed |
|---|---|---|---|
| Qwen3.8-Flash-Next Qwen3.8 | 109.7 GB | 25–51 tok/s | |
| Qwen 3.5 122B-A10B Qwen 3.5 | 74.5 GB | 11–24 tok/s | |
| Nemotron 3 Super 120B-A12B Nemotron 3 Super | 73.3 GB | 10–21 tok/s | |
| Nemotron 3.5 Super VL 120B-A12B Nemotron 3.5 | 73.3 GB | 10–21 tok/s | |
| GPT-OSS 120B GPT-OSS | 71.6 GB | 27–56 tok/s | |
| Qwen3-Coder-Next (80B-A3B MoE) Qwen3-Coder | 49.4 GB | 40–84 tok/s | |
| Kolibri 1 Kolibri | 48.5 GB | 37–76 tok/s | |
| Nemotron 3.5 Bolt 74B Nemotron 3.5 | 45.6 GB | 18–37 tok/s | |
| K2 Horizon MoVA 36B-A4B K2 Horizon | 25 GB | 23–49 tok/s | |
| Qwen 3.6 35B-A3B Qwen 3.6 | 22.2 GB | 41–86 tok/s | |
| Nex-N2.5 mini Nex-N2.5 | 21.9 GB | 25–53 tok/s | |
| Nex-N2 mini Nex-N2 | 21.9 GB | 25–53 tok/s |
Buy it or rent the same memory
Buy the card, or rent a GPU with the same memory by the hour to try models first.
As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.
Speed vs other GPUs
Llama 3.1 8B, Q4_K_M. Estimated ranges. How this is calculated
Specifications
Specs last updated 2026-07-12.
- Memory
- 128 GB
- Memory bandwidth
- 256 GB/s
- Architecture
- Zen 5 + RDNA 3.5 "Strix Halo"
- Series
- AI Workstation
- Board power
- 120 W
- Release year
- 2025
- Usable for models
- 128 GB
Similar GPUs
Frequently asked questions
Can the AMD Ryzen AI Max+ 395 run local LLMs?
Yes. With 128 GB (128 GB usable by a model) it runs 141 of the catalogued models at Q4_K_M with 8K context; the largest is Qwen3.8-Flash-Next, needing about 109.7 GB.
How fast is the AMD Ryzen AI Max+ 395 for AI inference?
It is estimated to run Llama 3.1 8B at 18–38 tok/s at Q4_K_M. Llama 3.3 70B is estimated at 2.4–5.1 tok/s. These are modelled estimates from memory bandwidth, not measurements; the methodology page shows the formula.
What LLMs can I run on 128 GB?
Among the best that fit: Qwen3.8-Flash-Next, Qwen 3.5 122B-A10B, Nemotron 3 Super 120B-A12B, Nemotron 3.5 Super VL 120B-A12B, GPT-OSS 120B. The quickest start is Ollama: ollama run llama3.3:70b.
Keep going
Can I run it on the AMD Ryzen AI Max+ 395?
More for this card
Tools