Local AI workstation
A maximum-capacity single-GPU workstation with 96 GB ECC VRAM and 256 GB eight-channel ECC system memory.
AI strength score
AI strength score
What this score is based on
Headroom for large local models and demanding AI work.
Value
Value
What this score is based on
Weak 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
€33,150
Time range
The chart slider reports the estimated system total by date.
| Date | System estimate | CPU | GPU | RAM | Storage | Motherboard | PSU | Case | Cooler |
|---|---|---|---|---|---|---|---|---|---|
| 1 Jul | €33,135 | €4,400 | €13,900 | €8,109 | €1,200 | €1,359 | €459 | €164 | €152 |
| 6 Jul | €33,135 | €4,400 | €13,900 | €8,109 | €1,200 | €1,359 | €459 | €164 | €152 |
| 11 Jul | €33,135 | €4,400 | €13,900 | €8,109 | €1,200 | €1,359 | €459 | €164 | €152 |
| 16 Jul | €33,135 | €4,400 | €13,900 | €8,109 | €1,200 | €1,359 | €459 | €164 | €152 |
| 21 Jul | €33,135 | €4,400 | €13,900 | €8,109 | €1,200 | €1,359 | €459 | €164 | €152 |
| 26 Jul | €33,135 | €4,400 | €13,900 | €8,109 | €1,200 | €1,359 | €459 | €164 | €152 |
| 31 Jul | €33,135 | €4,400 | €13,900 | €8,109 | €1,200 | €1,359 | €459 | €164 | €152 |
| 5 Aug | €33,135 | €4,400 | €13,900 | €8,109 | €1,200 | €1,359 | €459 | €164 | €152 |
| 10 Aug | €33,135 | €4,400 | €13,900 | €8,109 | €1,200 | €1,359 | €459 | €164 | €152 |
| 15 Aug | €33,150 | €4,400 | €13,900 | €8,109 | €1,200 | €1,359 | €459 | €178 | €152 |
| 20 Aug | €33,150 | €4,400 | €13,900 | €8,109 | €1,200 | €1,359 | €459 | €178 | €152 |
| 25 Aug | €33,150 | €4,400 | €13,900 | €8,109 | €1,200 | €1,359 | €459 | €178 | €152 |
| 30 Aug | €33,150 | €4,400 | €13,900 | €8,109 | €1,200 | €1,359 | €459 | €178 | €152 |
| 4 Sept | €33,150 | €4,400 | €13,900 | €8,109 | €1,200 | €1,359 | €459 | €178 | €152 |
| 9 Sept | €33,150 | €4,400 | €13,900 | €8,109 | €1,200 | €1,359 | €459 | €178 | €152 |
| 14 Sept | €33,150 | €4,400 | €13,900 | €8,109 | €1,200 | €1,359 | €459 | €178 | €152 |
| 19 Sept | €33,150 | €4,400 | €13,900 | €8,109 | €1,200 | €1,359 | €459 | €178 | €152 |
| 24 Sept | €33,150 | €4,400 | €13,900 | €8,109 | €1,200 | €1,359 | €459 | €178 | €152 |
| 29 Sept | €33,150 | €4,400 | €13,900 | €8,109 | €1,200 | €1,359 | €459 | €178 | €152 |
CPU
AMD Ryzen Threadripper PRO 9975WX
GPU
PNY NVIDIA RTX PRO 6000 Blackwell Workstation Edition 96GB
VRAM
96 GB
RAM
256 GB
Storage
8000 GB
Recommended model class
70B-class quantized inference with long-context headroom after exact workload validation
Throughput
Runtime qualification required; no fixed throughput promise
System power
~950 W
Recommended PSU
1600 W
Cooling
Full-IHS sTR5 workstation air cooling with a full-tower airflow path
Component rows show Estonian market or reference prices. Service, assembly, and configuration are shown separately below.
| Component | Product | Estimated market price |
|---|---|---|
| CPU | AMD Ryzen Threadripper PRO 9975WX | €4,620 |
| GPU | PNY NVIDIA RTX PRO 6000 Blackwell Workstation Edition 96GB | €14,595 |
| RAM | Kingston FURY Renegade Pro 256GB (8x32GB) DDR5-5600 CL28 ECC RDIMM | €8,515 |
| Storage | WD Black SN850X 8TB | €1,260 |
| Motherboard | ASUS Pro WS WRX90E-SAGE SE | €1,427 |
| PSU | be quiet! Dark Power Pro 13 1600W | €482 |
| Case | Phanteks Enthoo Pro 2 Tempered Glass Black | €172 |
| Cooler | Noctua NH-U14S TR5-SP6 | €160 |
| Estimated component total | €31,230 | |
| Service / assembly / configuration fee | €3,437 | |
| Estimated build total | €34,667 | |
Recommended model
A capable MoE model that gives 32GB and 48GB workstations a meaningfully heavier coding target.
Usable
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: 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.
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: Usable
Likely good memory headroom for this quantized model at normal context sizes.
Assumptions
Family: Qwen3.6
Parameters: 35B
Structure: 35B total / 3B active MoE
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: 24 GB
Default estimate: 31.5 GB @ 8,192 tokens
Weights / KV / runtime / margin: 24 GB / 2.5 GB / 2 GB / 3 GB
CPU/RAM fallback: Not recommended
VRAM: 32 GB minimum / 48 GB recommended
RAM: 64 GB minimum / 64 GB recommended
Current run mode: Comfortable GPU fit
Expected experience: Usable
Full GPU offload: Only when the memory estimate and context fit
Context warning: Long repository context can use the remaining headroom quickly, especially on 32GB GPUs.
| Context | Weights | KV | Runtime | Margin | Estimated GPU memory |
|---|---|---|---|---|---|
| 4K | 24 GB | 1.5 GB | 2 GB | 3 GB | 30.5 GB |
| 8K | 24 GB | 2.5 GB | 2 GB | 3 GB | 31.5 GB |
| 16K | 24 GB | 5 GB | 2 GB | 3.5 GB | 34.5 GB |
| 32K | 24 GB | 10 GB | 2 GB | 4 GB | 40 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: Comfortable GPU fit
Expected experience: Fast
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: 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: 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: Comfortable GPU fit
Expected experience: Usable
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.
€34,667
Estimated total. Final price confirmed before ordering.
Request a quote