Images are for reference only. Refer to the linked store for actual product images.An integrated-graphics starting point for everyday work and lighter games, with a 16 GB dual-channel DDR4 kit. A discrete GPU can be added later. This USD budget is an illustrative planning target, not a verified parts total or a retailer quote. Check current local prices, BIOS support and mounting clearances. Images are for reference only. Refer to the linked store for actual product images.
Explore cloud use, local language models and image generation with the parts you selected. Memory estimates are not speed benchmarks.
A larger local GPU is not required just to chat with a cloud model or request cloud-generated images. Check the service account, availability in your region, internet connection and supported browser or client.
Local editing, 3D work and running several apps still use your PC’s resources. This does not guarantee a service’s response time.
How cloud inference worksCPU and shared-memory graphics paths depend on the application; shared RAM is not dedicated VRAM.
Image size, batch size, model components and extra nodes change memory use. CPU offloading can reduce VRAM demand but may be slow. Video generation, training and fine-tuning require separate assessments.
ComfyUI hardware requirementsModel memory and offloadingChange the assumptions to explore the memory tradeoff. These are model sizes, not recommendations for a specific model.
Theoretical weight storage only: 3.7 GiB · 8B / 4-bit
Actual use is higher: quantization metadata, unquantized tensors, KV cache, compute buffers and the runtime also need memory. Total installed memory is not the same as free memory.
| Parameters | Weight lower bound | Compared with selected VRAM |
|---|---|---|
| 3B | 1.4 GiB | Not verified |
| 8B | 3.7 GiB | Not verified |
| 14B | 6.5 GiB | Not verified |
| 32B | 14.9 GiB | Not verified |
| 70B | 32.6 GiB | Not verified |
Weight lower bound = total parameters × bits ÷ 8. B means one billion parameters; GiB means 2³⁰ bytes. All parameters are counted, including inactive experts in a mixture-of-experts model. Nominal catalog RAM and VRAM capacities are used as GiB for this planning comparison.
Shared system memory is not added to dedicated VRAM. RAM kit capacity is counted once. Already-owned parts still count as installed hardware. No throughput or “smooth performance” claim is made.
After assembly, use the actual model file and context setting with the runtime’s resource estimator, then measure response speed and memory use in your workload.
LM Studio resource estimationWeight estimates · Context and memory · GPU runtime support · Application requirements
AI documentation checked: 2026-09-19A desktop for everyday tasks and a starting point for trying lighter games without buying a separate graphics card. Check the actual application's requirements before treating integrated graphics as sufficient.
The Ryzen 5 5600GT supplies the graphics path, so the initial list can omit a discrete GPU. The B550M Pro4 and DDR4 kit keep the selection on AM4 rather than requiring an AM5 board and DDR5.
The 16 GB kit uses two modules. The 500 GB NV3 keeps the initial storage scope small; list the operating system, applications and files you need before accepting that capacity.
The micro-ATX Q300L and single-tower Assassin X make this a conventional air-cooled layout. The listed 550 W PSU is a starting selection, not permission to add any graphics card.
If a game or application needs more graphics performance, compare the complete cost of a discrete GPU, any PSU change and additional case cooling. For office work, storage capacity may be the more useful first change.
This is an editorial parts-list explanation. The planning target is not a current retailer total, and this configuration has not been benchmarked by RigAtlas.