VRAM
Memory on the graphics card; usually the main limit for local AI model size.
LLMLab.ee
AI Workstations in Estonia
Framework Desktop (Custom)
Framework compact AI system
Honest visual overview
Product schematic
A schematic summary of the key facts before reviewing price and fit.
This is a schematic summary, not a photo of the exact build.
Type
compact ai system
Chip
AMD Ryzen AI MAX 395+
Memory
64GB unified
Purchase mode
Quote review
Details
Chip
AMD Ryzen AI MAX 395+
Memory
64GB unified
Storage
1000GB SSD
GPU Class
Integrated Radeon 8050S
Installed Software
Ubuntu 24.04, ROCm, PyTorch, Ollama, Docker
Stock
In Stock
Better for 30B-class models
Stronger fit for larger quantized models; actual fit depends on runtime and settings.
AI terms in plain language
Unified memory
Apple Silicon memory shared by CPU and GPU. Useful for local AI, but not identical to NVIDIA VRAM.
7B / 13B / 70B
A rough model-size signal. Larger numbers usually need more memory and may run slower.
q4 / quantization
A compressed 4-bit model that uses less memory, sometimes with quality or speed tradeoffs.
Estimated Market Pricing
Estonian market reference estimate before assembly. Used to prepare your custom quote.
Planning reference priceIncludes 15% assembly markup
No historical pricing yet.
This product is newly added or awaiting market data collection.
When history is available, charts show the Estonian market average before assembly markup.
Pricing & Purchase
Quote reference price: €1724
Planning reference price
Shown for planning. Direct checkout remains quote-only until fresh market pricing and availability are checked.
Quote-only until fresh market pricing is available.
Fresh, non-fallback Estonian market pricing is required before Stripe payment can be opened. Use the verified quote request on this page for manual review.
What happens after your quote request
- No payment is taken from the quote request form.
- We review your use case, model targets, timeline, and budget.
- We verify suitable parts and current Estonian market pricing.
- Possible substitutions or changes are confirmed before any payment link.
- We usually send the next step or follow-up questions within 1-2 business days.
Support and questions continue through the order or quote email thread.
Request a verified quote
The request does not take payment. Price, availability, and possible substitutions are confirmed before any payment link.
Practical model fit
Local AI examples
Examples for Framework Desktop (Custom), based mainly on GPU VRAM and system memory.
Good fit for private chatGood fit for document summariesNot ideal for 70B+ models
Starter pick
Llama 3.2 3B Instruct
A small, friendly starter model for learning local AI without needing a large GPU.
It is easy to download, small enough for almost any LLMLab machine, and useful for basic private chat.
Possible with caveats
ollama run llama3.2
Should be possible with Q4 quantization, but context length or partial CPU offload can slow it down.
Qwen3 4B
Light chat, multilingual prompts, compact reasoning tests
A compact Qwen model that gives beginners a taste of newer reasoning-style local models.
CPU-only should be possible for this small model, but GPU acceleration will feel better.
Llama 3.3 70B Instruct
High-end local chat experiments on 48GB+ systems
A high-end warning example: useful on serious hardware, but not a normal beginner target.
No suitable GPU or unified-memory headroom was inferred for this model.
Expandable technical details
Assumptions
- System RAM: 64GB.
- Ratings assume Q4-style quantization, moderate context, one local model running at a time. Treat them as fit guidance, not a speed estimate.
- Compact-system fit depends on the installed runtime and GPU backend, especially for Intel and AMD systems.
Llama 3.2 3B Instruct technical details
Family: Meta Llama 3.2
Parameters: 3B
Quantization: Q4_K_M
Approx. model size: 2GB
CPU-only: Possible
VRAM: 0GB min / 4GB recommended
RAM: 8GB min / 16GB recommended
Full GPU offload: Should be possible when memory fits
Context warning: Long documents can still push memory use up, even with a small model.
Research sources
Researched: 2026-06-22
Qwen3 4B technical details
Family: Qwen3
Parameters: 4B
Quantization: Q4_K_M
Approx. model size: 2.5GB
CPU-only: Possible
VRAM: 4GB min / 6GB recommended
RAM: 8GB min / 16GB recommended
Full GPU offload: Should be possible when memory fits
Context warning: Keep the context window modest on 8GB to 16GB systems.
Llama 3.3 70B Instruct technical details
Family: Meta Llama 3.3
Parameters: 70B
Quantization: Q4_K_M
Approx. model size: 42.52GB
CPU-only: Not recommended
VRAM: 48GB min / 64GB recommended
RAM: 64GB min / 128GB recommended
Full GPU offload: Often limited
Context warning: 70B at Q4 is already around 43GB before extra context overhead.
Research sources
Researched: 2026-06-22
Local AI performance is approximate. Results depend on quantization, context length, backend, drivers, RAM, and whether the model fits fully in VRAM.
Trust and process
What happens after an order or quote request
After payment
You receive a confirmation email. We then check part availability and contact you if any component may need a practical substitution.
Assembly and testing
The planned workflow is assembly, software setup, and baseline GPU/AI checks before handover.
Handover in Estonia
Pickup or local delivery method and timing are agreed after availability is checked.
Warranty and support
Warranty handling depends on the component, manufacturer, and retailer. Support questions continue through the order or quote email thread.
Assembly QA
Planned baseline checks before handover
- BIOS and firmware baseline check
- Driver and AI tooling installation
- Thermal and load sanity check
- Memory and storage health check
- Local AI smoke test where applicable
Trust details
Important before ordering
Contact and support
Questions continue through the order or quote email thread. Replying to the confirmation is the fastest path.
Warranty
Warranty handling depends on the component, manufacturer, and retailer; the practical path is confirmed case by case.
Handover in Estonia
Pickup or local delivery method and timing are agreed after availability is checked.
Cancellations and changes
Cancellations and changes are confirmed in writing through the quote or order thread; after sourcing or assembly begins, custom-order handling may depend on order state.
Payment security
Card details are entered in Stripe checkout. LLMLab.ee does not collect or store full card numbers.
Pricing method
We show the Estonian market average before assembly and the order price with the 15% assembly and configuration markup.