GEEKOM A9 Max
Ryzen AI 9 HX 370 · AI Productivity PC
The GEEKOM A9 Max is GEEKOM's mini pc built on the Ryzen AI 9 HX 370, and it gives a local model about 16GB of usable AI memory at 120 GB/s. The 32GB / 2TB configuration is $1,599 at Amazon, verified 5h ago. It scores 20.9 overall on the AIPC Score.
Price and memory shown are for the 32GB / 2TB configuration.
AIPC Score: 20.9
- AI memory16.7
- AI compute6.6
- Memory bandwidth6.7
- Model compatibility34.5
- GPU capability6.6
- NPU capability50
- Software support40
- Power efficiency22.9
- Expandability70
- Price/value12.5
Specifications
- AI Memory
- 16GB
- CPU
- AMD Ryzen AI 9 HX 370
- GPU
- Radeon 890M
- NPU
- XDNA 2 (50 TOPS)
- Memory bandwidth
- 120 GB/s
- Storage
- 2TB
- Configuration
- 32GB / 2TB
- Type
- Mini PC
How we calculate AI memory: About half of system memory, the usual share for integrated graphics. Source →
Configurations
| Configuration | AI Memory | Memory bandwidth | Price | Retailer |
|---|---|---|---|---|
| 32GB / 2TB | 16GB | 120 GB/s | $1,599 | Amazon (third-party seller) |
| 64GB / 2TB | 32GB | 120 GB/s | No verified price | — |
What can this PC run?
| Model | Quantization | Fits | Mode | State | Speed |
|---|---|---|---|---|---|
| DeepSeek-R1-Distill-Qwen-7B | Q4 | Yes | Full memory | Calculated | Performance not yet benchmarked |
| DeepSeek-R1-Distill-Qwen-7B | Q8 | Yes | Full memory | Calculated | Performance not yet benchmarked |
| DeepSeek-R1-Distill-Qwen-14B | Q4 | Yes | Full memory | Calculated | Performance not yet benchmarked |
| Gemma 3 4B IT | Q4 | Yes | Full memory | Calculated | Performance not yet benchmarked |
| Gemma 3 4B IT | Q8 | Yes | Full memory | Calculated | Performance not yet benchmarked |
| Gemma 3 12B IT | Q4 | Yes | Full memory | Calculated | Performance not yet benchmarked |
| Gemma 3 12B IT | Q8 | Limited | Offload required | Calculated | Performance not yet benchmarked |
| Llama 3.2 3B Instruct | Q4 | Yes | Full memory | Calculated | Performance not yet benchmarked |
| Llama 3.2 3B Instruct | Q8 | Yes | Full memory | Calculated | Performance not yet benchmarked |
| Llama 3.1 8B Instruct | Q4 | Yes | Full memory | Calculated | Performance not yet benchmarked |
| Llama 3.1 8B Instruct | Q8 | Yes | Full memory | Calculated | Performance not yet benchmarked |
| Mistral Small 3 (Mistral-Small-24B-Instruct-2501) | Q4 | Limited | Offload required | Calculated | Performance not yet benchmarked |
| Devstral Small 1.1 (Devstral-Small-2507) | Q4 | Limited | Offload required | Calculated | Performance not yet benchmarked |
| Phi-4 | Q4 | Yes | Full memory | Calculated | Performance not yet benchmarked |
| Phi-4 | Q8 | Limited | Offload required | Calculated | Performance not yet benchmarked |
| Qwen3-4B | Q4 | Yes | Full memory | Calculated | Performance not yet benchmarked |
| Qwen3-4B | Q8 | Yes | Full memory | Calculated | Performance not yet benchmarked |
| Qwen3-8B | Q4 | Yes | Full memory | Calculated | Performance not yet benchmarked |
| Qwen3-8B | Q8 | Yes | Full memory | Calculated | Performance not yet benchmarked |
| Qwen3-14B | Q4 | Yes | Full memory | Calculated | Performance not yet benchmarked |
| gpt-oss-20b | Q4 | Limited | Offload required | Calculated | Performance not yet benchmarked |
| Whisper large-v3 | Published | Yes | Full memory | Calculated | Performance not yet benchmarked |
| Stable Diffusion XL Base 1.0 | Published | Yes | Full memory | Calculated | Performance not yet benchmarked |
| Stable Diffusion 3.5 Large | Published | Limited | Offload required | Calculated | Performance not yet benchmarked |
Does not fit (42)
- DeepSeek-R1-Distill-Qwen-14B Q8: needs 20.3GB
- DeepSeek-R1-Distill-Qwen-32B Q4: needs 25GB
- DeepSeek-R1-Distill-Qwen-32B Q8: needs 42.3GB
- DeepSeek-R1-Distill-Llama-70B Q4: needs 51.5GB
- DeepSeek-R1-Distill-Llama-70B Q8: needs 88.8GB
- DeepSeek-R1 Q4: needs 469.8GB
- DeepSeek-R1 Q8: needs 821.9GB
- DeepSeek-V3 Q4: needs 469.8GB
- DeepSeek-V3 Q8: needs 821.9GB
- GLM-5.2 Q4: needs 527GB
- GLM-5.2 Q8: needs 922.1GB
- Gemma 3 27B IT Q4: needs 20.8GB
- Gemma 3 27B IT Q8: needs 35GB
- Kimi-K2-Instruct Q4: needs 699.2GB
- Kimi-K2-Instruct Q8: needs 1223.9GB
- Llama 3.1 70B Instruct Q4: needs 50.8GB
- Llama 3.1 70B Instruct Q8: needs 87.5GB
- Llama 3.3 70B Instruct Q4: needs 50.8GB
- Llama 3.3 70B Instruct Q8: needs 87.5GB
- Llama 4 Scout 17B-16E Instruct Q4: needs 78GB
- Llama 4 Scout 17B-16E Instruct Q8: needs 135.2GB
- Llama 4 Maverick 17B-128E Instruct Q4: needs 280.9GB
- Llama 4 Maverick 17B-128E Instruct Q8: needs 490.7GB
- Mistral Small 3 (Mistral-Small-24B-Instruct-2501) Q8: needs 31.3GB
- Devstral Small 1.1 (Devstral-Small-2507) Q8: needs 31.3GB
- Mistral Medium 3.5 128B Q4: needs 91.2GB
- Mistral Medium 3.5 128B Q8: needs 158.4GB
- Qwen3-14B Q8: needs 20.1GB
- Qwen3-30B-A3B Q4: needs 23.3GB
- Qwen3-30B-A3B Q8: needs 39.3GB
- Qwen3-32B Q4: needs 24.9GB
- Qwen3-32B Q8: needs 42.1GB
- Qwen3-235B-A22B Q4: needs 165.8GB
- Qwen3-235B-A22B Q8: needs 289.1GB
- gpt-oss-20b Q8: needs 27.7GB
- gpt-oss-120b Q4: needs 83.6GB
- gpt-oss-120b Q8: needs 145GB
- FLUX.1 schnell Published: needs 27.4GB
- FLUX.1 dev Published: needs 27.4GB
- HunyuanVideo Published: needs 60GB
- Wan2.1 T2V 14B Published: needs 65.7GB
- Wan2.2 T2V A14B Published: needs 80GB
Alternatives
- Apple Mac mini (M5 Pro)
18GB · AI Score 21.2
$1,549
- Minisforum AI X1 Pro-470
16GB · AI Score 20.5
$1,459
- Minisforum AI X1 Pro-370
16GB · AI Score 20
$1,247