AMD Ryzen AI 9 HX 370 for local LLMs
Written by Jakub Rusinowski · Last updated
With 32 GB of LPDDR5X at 120 GB/s, the AMD Ryzen AI 9 HX 370 runs 122 catalogued models at Q4_K_M with 8K context. The largest that fits is K2 Horizon MoVA 36B-A4B (~25 GB), and the top pick is K2 Horizon MoVA 36B-A4B at 12–24 tok/s.
Strix POINT, not Strix Halo: 12 Zen 5 cores with a 16-CU Radeon 890M on a 128-bit memory bus. 120 GB/s reflects the LPDDR5X-7500 fitted in machines like the Beelink SER9; AMD's own spec page quotes 89.6 GB/s for DDR5-5600 configurations, so the figure depends on the memory a builder solders down. Either way it is roughly half the Ryzen AI Max+ 395 this catalogue used to model it as.
Models that run on the AMD Ryzen AI 9 HX 370
Q4_K_M, 8K context, 32 GB usable. Ranked by quality and speed.
| Model | Memory · marker = 32 GB | VRAM | Speed |
|---|---|---|---|
| K2 Horizon MoVA 36B-A4B K2 Horizon | 25 GB | 12–24 tok/s | |
| Qwen 3.6 35B-A3B Qwen 3.6 | 22.2 GB | 22–45 tok/s | |
| Nex-N2.5 mini Nex-N2.5 | 21.9 GB | 13–27 tok/s | |
| Nex-N2 mini Nex-N2 | 21.9 GB | 13–27 tok/s | |
| Qwen 3.5 35B-A3B Qwen 3.5 | 21.9 GB | 13–27 tok/s | |
| Laguna XS 2.1 33B-A3B Poolside Laguna XS 2.1 | 20.7 GB | 13–27 tok/s | |
| Nemotron-Cascade 2 30B-A3B Nemotron Cascade 2 | 19.9 GB | 12–25 tok/s | |
| Qwen 3 30B-A3B (MoE) Qwen 3 | 20 GB | 17–34 tok/s | |
| Qwen3-Coder 30B-A3B (MoE) Qwen3-Coder | 20 GB | 17–34 tok/s | |
| GLM-4.7-Flash 30B-A3B GLM-4.7 / GLM-Z1 | 18.9 GB | 13–27 tok/s | |
| Nemotron 3 Nano Omni 30B-A3B Nemotron 3 Nano Omni | 18.9 GB | 13–27 tok/s | |
| North Mini Code 1.0 30B-A3B North Mini Code | 18.9 GB | 13–27 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 2026-09-19.
- Memory
- 32 GB LPDDR5X
- Memory bandwidth
- 120 GB/s
- Memory bus
- 128-bit
- Architecture
- Zen 5 + RDNA 3.5 "Strix Point"
- Series
- Ryzen AI 300
- Board power
- 54 W
- Laptop TGP range
- 28–54 W
- Release year
- 2024
- Compute backends
- ROCM, VULKAN
- Usable for models
- 32 GB
Similar GPUs
Frequently asked questions
Can the AMD Ryzen AI 9 HX 370 run local LLMs?
Yes. With 32 GB (32 GB usable by a model) it runs 122 of the catalogued models at Q4_K_M with 8K context; the largest is K2 Horizon MoVA 36B-A4B, needing about 25 GB.
How fast is the AMD Ryzen AI 9 HX 370 for AI inference?
It is estimated to run Llama 3.1 8B at 9.0–19 tok/s at Q4_K_M. Llama 3.3 70B does not fit: it needs about 44 GB against 32 GB usable. These are modelled estimates from memory bandwidth, not measurements; the methodology page shows the formula.
What LLMs can I run on 32 GB?
Among the best that fit: K2 Horizon MoVA 36B-A4B, Qwen 3.6 35B-A3B, Nex-N2.5 mini, Nex-N2 mini, Qwen 3.5 35B-A3B.