Can Desktop PC · 2× GeForce RTX 3090 (48 GB) · 128 GB RAM run MiniCPM5 2B?
48 GB VRAM + 128 GB RAM · 936 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 Ollama. Generation: 170–280 tok/s, leaving about 43 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 | 170–280 tok/s | under 1 s | 8K | Details |
| Coding questionswith Continue | Comfortable | Q8_0 | 160–260 tok/s | under 1 s | 16K | Details |
| Coding in a repositorywith Aider | Acceptable | Q8_0 | 140–230 tok/s | ≈1 s | 32K | Details |
| Agentic codingwith OpenCode | Acceptable | Q8_0 | 130–210 tok/s | ≈2 s | 32K | Details |
| Long documents (64K)with Open WebUI | Comfortable | Q8_0 | 95–160 tok/s | ≈5 s | 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 Desktop PC · 2× GeForce RTX 3090 (48 GB) · 128 GB RAM
The best-rated models for chat on this machine.
- Qwen3.6 35B-A3B140–230 tok/sExcellent
- Gemma 4 26B-A4B110–180 tok/sExcellent
- Qwen3.5 35B-A3B140–230 tok/sExcellent
- LFM2.5 24B-A2B270–450 tok/sExcellent
- gpt-oss-20b160–270 tok/sExcellent
- GLM-4.7-Flash (30B-A3B)130–220 tok/sExcellent
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.