Local AI workstation
A cooler, lower-cost alternative to the main 4K build while retaining 16GB CUDA memory
AI strength score
AI strength score
What this score is based on
For everyday local AI, coding help, and document work.
Value
Value
What this score is based on
Modest local-AI capability for the current estimated price.
Comfortable
Possible with limits
Not recommended
Uses market prices where available and reference estimates for the rest.
Reference estimate
€4,346
Time range
The chart slider reports the estimated system total by date.
| Date | System estimate | CPU | GPU | RAM | Storage | Motherboard | PSU | Case | Cooler |
|---|---|---|---|---|---|---|---|---|---|
| 16 Jun | €4,377 | €311 | €1,371 | €812 | €605 | €151 | €132 | €144 | €44 |
| 21 Jun | €4,034 | €311 | €1,039 | €812 | €605 | €150 | €132 | €144 | €44 |
| 26 Jun | €4,034 | €311 | €1,039 | €812 | €605 | €150 | €132 | €144 | €44 |
| 1 Jul | €4,034 | €311 | €1,039 | €812 | €605 | €150 | €132 | €144 | €44 |
| 6 Jul | €4,034 | €311 | €1,039 | €812 | €605 | €150 | €132 | €144 | €44 |
| 11 Jul | €4,034 | €311 | €1,039 | €812 | €605 | €150 | €132 | €144 | €44 |
| 16 Jul | €4,034 | €311 | €1,039 | €812 | €605 | €150 | €132 | €144 | €44 |
| 21 Jul | €4,034 | €311 | €1,039 | €812 | €605 | €150 | €132 | €144 | €44 |
| 26 Jul | €4,034 | €311 | €1,039 | €812 | €605 | €150 | €132 | €144 | €44 |
| 31 Jul | €4,034 | €311 | €1,039 | €812 | €605 | €150 | €132 | €144 | €44 |
| 5 Aug | €4,193 | €304 | €1,199 | €812 | €605 | €150 | €132 | €144 | €44 |
| 10 Aug | €4,202 | €304 | €1,199 | €812 | €605 | €159 | €132 | €144 | €44 |
| 15 Aug | €4,169 | €304 | €1,199 | €812 | €573 | €159 | €132 | €144 | €44 |
| 20 Aug | €4,169 | €304 | €1,199 | €812 | €573 | €159 | €132 | €144 | €44 |
| 25 Aug | €4,346 | €304 | €1,371 | €812 | €573 | €159 | €132 | €144 | €44 |
| 30 Aug | €4,346 | €304 | €1,371 | €812 | €573 | €159 | €132 | €144 | €44 |
| 4 Sept | €4,346 | €304 | €1,371 | €812 | €573 | €159 | €132 | €144 | €44 |
| 9 Sept | €4,346 | €304 | €1,371 | €812 | €573 | €159 | €132 | €144 | €44 |
| 14 Sept | €4,346 | €304 | €1,371 | €812 | €573 | €159 | €132 | €144 | €44 |
CPU
AMD Ryzen 7 9700X
GPU
PNY GeForce RTX 5070 Ti 16GB Triple Fan
VRAM
16 GB
RAM
64 GB
Storage
4000 GB
Recommended model class
7B-14B q4 + high-refresh 1440p gaming
Throughput
~182 t/s generation: Llama 2 7B Q4_0 in llama.cpp (CUDA, Flash Attention)
System power
~430 W
Recommended PSU
750 W
Cooling
Dual-tower air cooling
Component rows show Estonian market or reference prices. Service, assembly, and configuration are shown separately below.
| Component | Product | Estimated market price |
|---|---|---|
| CPU | AMD Ryzen 7 9700X | €327 |
| GPU | PNY GeForce RTX 5070 Ti 16GB Triple Fan | €1,439 |
| RAM | Patriot Viper Venom 64GB (2x32GB) DDR5-6000 CL30 AMD EXPO | €852 |
| Storage | WD Black SN850X 4TB | €636 |
| Motherboard | Gigabyte B650 EAGLE AX | €158 |
| PSU | SeaSonic Focus GX-750 750W | €138 |
| Case | Fractal Design North Charcoal Black TG Dark | €151 |
| Cooler | Thermalright Phantom Spirit 120 | €46 |
| Estimated component total | €3,748 | |
| Service / assembly / configuration fee | €812 | |
| Estimated build total | €4,560 | |
Recommended model
A current multimodal everyday model that makes good use of a 16GB GPU.
Fast
Likely good memory headroom for this quantized model at normal context sizes.
Private chat, coding help, document summaries, and image questions
A strong everyday model for 12GB-class GPUs and a practical coding pick when speed matters.
Expected experience: Fast
Likely good memory headroom for this quantized model at normal context sizes.
Serious coding help, complex reasoning, and longer document analysis
A strong dense model for 24GB to 32GB GPUs and higher-memory Apple systems.
Expected experience: Very slow
Offload-heavy experiment only: expect slower responses and keep context short. This is not a normal recommended target.
High-end local chat experiments on 48GB GPUs or 96GB+ Apple systems
A clear upper-limit example for checking whether a machine can attempt a 70B-class model.
Expected experience: Not recommended
This model needs roughly 51GB GPU memory at Q4_K_M with moderate context; this machine has about 16GB VRAM.
Assumptions
Family: Google Gemma 4
Parameters: 11.95B
Structure: 11.95B dense
License: Apache License 2.0; allowed. For guidance only; review the model licence before commercial use.
Native context: 262,144 tokens
Quantization: Q4_0 QAT
Approx. Q4 weights: 7.2 GB
Default estimate: 11.5 GB @ 8,192 tokens
Weights / KV / runtime / margin: 7.2 GB / 1.5 GB / 1.2 GB / 1.5 GB
CPU/RAM fallback: Not recommended
VRAM: 12 GB minimum / 16 GB recommended
RAM: 24 GB minimum / 32 GB recommended
Current run mode: Comfortable GPU fit
Expected experience: Fast
Full GPU offload: Only when the memory estimate and context fit
Context warning: Its large context window still requires substantial KV-cache headroom.
| Context | Weights | KV | Runtime | Margin | Estimated GPU memory |
|---|---|---|---|---|---|
| 4K | 7.2 GB | 1 GB | 1.2 GB | 1.5 GB | 11 GB |
| 8K | 7.2 GB | 1.5 GB | 1.2 GB | 1.5 GB | 11.5 GB |
| 16K | 7.2 GB | 2.5 GB | 1.2 GB | 1.5 GB | 12.5 GB |
| 32K | 7.2 GB | 5 GB | 1.2 GB | 2 GB | 15.5 GB |
Swipe the table sideways to inspect every memory estimate.
Research sources
Researched: 2026-07-30
Family: Qwen3.5
Parameters: 9B
Structure: 9B dense
License: Apache License 2.0; allowed. For guidance only; review the model licence before commercial use.
Native context: 262,144 tokens
Extended context: 1,010,000 via YaRN; not a default fit assumption
Quantization: Q4_K_M
Approx. Q4 weights: 6.6 GB
Default estimate: 11 GB @ 8,192 tokens
Weights / KV / runtime / margin: 6.6 GB / 1.5 GB / 1.2 GB / 1.5 GB
CPU/RAM fallback: Not recommended
VRAM: 8 GB minimum / 12 GB recommended
RAM: 16 GB minimum / 32 GB recommended
Current run mode: Comfortable GPU fit
Expected experience: Fast
Full GPU offload: Only when the memory estimate and context fit
Context warning: Start around 8K context even though the model supports much more.
| Context | Weights | KV | Runtime | Margin | Estimated GPU memory |
|---|---|---|---|---|---|
| 4K | 6.6 GB | 1 GB | 1.2 GB | 1.5 GB | 10.5 GB |
| 8K | 6.6 GB | 1.5 GB | 1.2 GB | 1.5 GB | 11 GB |
| 16K | 6.6 GB | 2.5 GB | 1.2 GB | 1.5 GB | 12 GB |
| 32K | 6.6 GB | 5 GB | 1.2 GB | 2 GB | 15 GB |
Swipe the table sideways to inspect every memory estimate.
Family: Qwen3.6
Parameters: 27B
Structure: 27B dense
License: Apache License 2.0; allowed. For guidance only; review the model licence before commercial use.
Native context: 262,144 tokens
Extended context: 1,010,000 via YaRN; not a default fit assumption
Quantization: Q4_K_M
Approx. Q4 weights: 17 GB
Default estimate: 23 GB @ 8,192 tokens
Weights / KV / runtime / margin: 17 GB / 2 GB / 1.5 GB / 2.5 GB
CPU/RAM fallback: Not recommended
VRAM: 24 GB minimum / 32 GB recommended
RAM: 48 GB minimum / 64 GB recommended
Current run mode: Partial GPU offload only
Expected experience: Very slow
Full GPU offload: Only when the memory estimate and context fit
Context warning: Repository-scale or very long document context can push a 24GB card beyond a comfortable fit.
| Context | Weights | KV | Runtime | Margin | Estimated GPU memory |
|---|---|---|---|---|---|
| 4K | 17 GB | 1 GB | 1.5 GB | 2.5 GB | 22 GB |
| 8K | 17 GB | 2 GB | 1.5 GB | 2.5 GB | 23 GB |
| 16K | 17 GB | 4 GB | 1.5 GB | 3 GB | 25.5 GB |
| 32K | 17 GB | 8 GB | 1.5 GB | 3.5 GB | 30 GB |
Swipe the table sideways to inspect every memory estimate.
Family: Meta Llama 3.3
Parameters: 70.60B
Structure: 70.6B dense
License: Llama 3.3 Community License; allowed with terms; gated access. For guidance only; review the model licence before commercial use.
Native context: 131,072 tokens
Quantization: Q4_K_M
Approx. Q4 weights: 42.5 GB
Default estimate: 51 GB @ 4,096 tokens
Weights / KV / runtime / margin: 42.5 GB / 3 GB / 1.5 GB / 4 GB
CPU/RAM fallback: Not recommended
VRAM: 48 GB minimum / 64 GB recommended
RAM: 64 GB minimum / 96 GB recommended
Current run mode: Not realistic here
Expected experience: Not recommended
Full GPU offload: Often limited
Context warning: The Q4 weights alone use about 42.5GB before KV cache, runtime overhead, and desktop headroom.
| Context | Weights | KV | Runtime | Margin | Estimated GPU memory |
|---|---|---|---|---|---|
| 4K | 42.5 GB | 3 GB | 1.5 GB | 4 GB | 51 GB |
| 8K | 42.5 GB | 6 GB | 1.5 GB | 4 GB | 54 GB |
| 16K | 42.5 GB | 12 GB | 1.5 GB | 4.5 GB | 60.5 GB |
| 32K | 42.5 GB | 24 GB | 1.5 GB | 5.5 GB | 73.5 GB |
Swipe the table sideways to inspect every memory estimate.
Local AI performance is approximate. Results depend on quantization, context length, backend, drivers, and whether the model plus KV cache fits in VRAM or Apple unified memory.
GPU memory and RAM
GPU memory usually limits model size; RAM supports apps, data, and model offload.
CUDA
NVIDIA’s software layer for many AI tools. Macs and AMD GPUs do not run CUDA workflows the same way.
Apple unified memory
Memory shared by the CPU, GPU, macOS, and apps; it is not the same as NVIDIA VRAM.
7B / 8B / 14B / 70B
Approximate model size in billions of parameters; larger models usually need more memory.
Quantized models
Lower-precision models, such as Q4, that use less memory with possible quality or speed tradeoffs.
Context length
How much text the model can keep in mind at once. Longer context uses more memory.
Inference
Running an existing model for chat, coding help, summaries, or document workflows.
Fine-tuning vs adapter tuning
LoRA and QLoRA train small adapters and need fewer resources than full fine-tuning.
Throughput (tokens/s)
Model output speed. Compare the same model, quantization, context, runtime, and user count; prompt processing is a separate measurement.
Here are similar setups in this category.
€4,560
Estimated total. Final price confirmed before ordering.
Request a quote