Choose model size
A quantized 8B model is modest. 32B and 70B models need considerably more memory but can cover more demanding tasks.
Local AI. Your hardware. Your data.
Find the right PC for your own local LLM
Work out how much model memory you really need, then compare complete systems for your model size, speed, space and budget.
- no cloud required
- memory-first guidance
- transparent evaluation
Three steps to the right class
Not every “AI PC” is a good LLM PC
For local language models, the crucial question is whether model weights, context cache and runtime headroom fit into fast memory together. An impressive NPU TOPS figure alone does not answer it.
Speed or capacity?
A discrete high-end GPU delivers excellent speed. Large unified memory can hold bigger models, with a different performance profile.
Check the exact system
Cooling, memory allocation, storage, upgradeability and the exact GPU configuration matter as much as the processor name.
Quick orientation
Which memory tier fits?
Compact models
A practical starting point for 7B to 14B models in suitable quantization and normal context lengths.
Chat · summarization · first coding workflowsMore quality and speed
Interesting for quantized 20B to 32B models or several smaller components with useful headroom.
Coding · RAG · capable assistantsLarge models
The capacity class for 70B models and long contexts, depending on runtime and quantization.
70B · long context · agent stacksThese values are conservative guidance, not a guarantee. Architecture, quantization, context, KV cache and runtime all change memory use.
Specific complete systems
Three hardware paths for local AI
Choose by model size and daily use: high memory capacity in a compact PC or very high GPU speed in a tower.
Capacity focus · compact
GMKtec EVO-X2
Ryzen AI Max+ 395 with 128 GB of unified memory and a 2 TB configuration: compelling when fitting a large quantized model matters more than maximum discrete-GPU speed.
- 128 GB unified memory
- 2 TB SSD configuration
- Compact form factor
Speed focus · desktop
Corsair Vengeance i8300
A high-end tower configuration combining a GeForce RTX 5090 32 GB with 64 GB of system memory. Suited to fast local inference where the active workload fits in GPU memory.
- 32 GB discrete VRAM
- 64 GB system memory
- Desktop cooling
Speed focus · desktop
HP OMEN 45L
This 64 GB / 2 TB tower configuration pairs a GeForce RTX 5090 with a large chassis. It targets fast 8B to 32B workflows while leaving room for system-side tools.
- 32 GB discrete VRAM
- 64 GB system memory
- 2 TB SSD configuration
* Paid link. We may earn a commission if you buy; your price is unchanged. As an Amazon Associate I earn from qualifying purchases. Please verify the exact configuration and current availability with the retailer.
Your workload matters
From model to suitable PC in about a minute
The finder considers model class, context length, intended use and your main priority. It returns an explainable hardware class, not false precision.
Choose by your main goal
Which kind of system actually helps?
Fast coding and RAG
For mostly 8B to 32B models, an RTX 5090 with 32 GB of VRAM is the speed-focused choice. Pair it with at least 64 GB of system RAM and 2 TB of NVMe storage.
RTX 5090 buying checkRun 70B at home
128 GB of unified memory can hold many quantized 70B models with useful reserve, though response speed remains below large professional GPUs.
Compare 70B hardware pathsKeep a large model library
The Corsair's included 6 TB is convenient for several quantizations and project data. With a 2 TB system, make sure another M.2 slot or fast external storage is available.
Compare storage and upgrades