Can Laptop · Ryzen AI 9 HX 370 (Radeon 890M) · 32 GB run MiniCPM5 2B?
32 GB unified · 120 GB/s memory bandwidth · MiniCPM5 2B has 2.5B parameters.
Short answer
Yes, excellent for chat and acceptable or better for every workload we test.
Best quantization for chat: Q8_0 (2.5 GB of weights) on Lemonade. Generation: 20–35 tok/s, leaving about 20 GB free for your other apps.
How it rates for each workload
Same model and machine, different jobs. Agents and long documents send far bigger prompts than chat, so they need much more speed and memory.
| Workload | Verdict | Quant | Generation | First reply | Context | |
|---|---|---|---|---|---|---|
| Chatwith Open WebUI | Excellent | Q8_0 | 20–35 tok/s | ≈1 s | 8K | Details |
| Coding questionswith Continue | Comfortable | Q8_0 | 20–35 tok/s | ≈6 s | 16K | Details |
| Coding in a repositorywith Aider | Acceptable | Q8_0 | 18–30 tok/s | ≈20 s | 32K | Details |
| Agentic codingwith OpenCode | Acceptable | Q8_0 | 17–30 tok/s | ≈25 s | 32K | Details |
| Long documents (64K)with Open WebUI | Comfortable | Q4_K_M | 16–25 tok/s | ≈2 min | 64K | Details |
Speeds are bandwidth-based estimates; no direct benchmark exists for this pair. “First reply” is the time to read the workload’s opening prompt. How we calculate
Other models for Laptop · Ryzen AI 9 HX 370 (Radeon 890M) · 32 GB
The best-rated models for chat on this machine.
- LFM2.5 24B-A2B35–60 tok/sExcellent
- gpt-oss-20b20–35 tok/sExcellent
- Qwen3.5 4B15–25 tok/sExcellent
- Llama 3.2 3B Instruct20–35 tok/sExcellent
- Gemma 4 26B-A4B16–25 tok/sComfortable
- GLM-4.7-Flash (30B-A3B)25–40 tok/sComfortable
Cheapest machines for MiniCPM5 2B
Hardware rated comfortable or better for chat, lowest price first.
Different tool, context size or workload?
These pages use typical settings. The full check models your exact setup.