Complete computer · Unified memory
Mac mini M5 Pro (15-core CPU, 16-core GPU) 24GB
New purchase estimate
9.3 GiB of spare memory
The lowest priced match. Enough memory and estimated speed for this workload, with more of your budget left over.
Choose a model. Compare memory fit, estimated tokens per second and hardware prices for your budget.
Find a setup by name, or select a point to highlight its price, speed and memory.
Include results that use the CPU and system RAM.
5 010,02 USD ceiling42 setups above this range · search still covers all hardware
↑ Faster · ← Lower cost
Select a point to highlight it, or search by name above.
16 systems have missing or unplottable values for these axes.
42 setups are above the 5 010,02 USD graph ceiling.
Search above or use Browse every setup below to explore the full hardware library.
Purchase estimates use the selected market; missing local prices use labeled FX estimates from another market. The price graph defaults to a ceiling of 125% of your budget. Use the full price range or search to explore more expensive setups. GPU prices include the configured host PC. Used prices where available; otherwise new.
YOUR HARDWARE SHORTLIST
Every pick fits your model, meets 30 tokens/s per user, and stays within budget.
Complete computer · Unified memory
New purchase estimate
9.3 GiB of spare memory
The lowest priced match. Enough memory and estimated speed for this workload, with more of your budget left over.
Complete computer · Unified memory
Used purchase estimate
17.3 GiB of spare memory
An estimated 100 W during inference. About 2 USD/month at 4 hours a day. A useful option when ongoing energy use matters.
Single GPU · Host included
Used purchase estimate
8.4 GiB of spare memory
Around 4.0× your speed target at the central estimate. A performance-focused option for more responsive generation.
Watch the same answer arrive at your target speed and on a system that fits your workload.
About 4.2 s for this ~125-token response.
Write a short passage about a neighborhood garden.
Press play to see this response take shape.
Requested pace 30 tok/s
About 1.1 s for this ~125-token response · 3 000 USD
Write a short passage about a neighborhood garden.
Press play to see this response take shape.
Central estimate 118.8 tok/s
Compare local language-model hardware by memory fit, estimated generation speed and price. GPU VRAM, Apple-style unified memory and CPU offload behave differently, so the same model and settings can produce very different trade-offs. Adjust the workload and budget to explore a practical shortlist.
It estimates whether a selected model, quantization and context can run on each listed system, then compares a range of per-user generation speeds. It also shows hardware prices where available. These are planning estimates based on hardware and software assumptions, not measured benchmarks or a promise that a particular setup will perform the same in your environment.
No. A discrete GPU usually has its own VRAM, while unified-memory systems let the processor and GPU share one memory pool. Ordinary system RAM can also hold model data, but moving it to a GPU over PCIe can limit speed. The simulator treats those memory paths differently; installed RAM plus VRAM should not be read as one equally fast pool.
Generation speed varies with backend, drivers, batch size, model implementation and other workload details. A range communicates that uncertainty more honestly than a single precise-looking number. The estimate describes decoding tokens per second per person; prompt processing and time to first token are separate parts of an end-to-end response. Check how fit and speed are estimated and the reported inference measurements before buying hardware.
It depends on the exact model, precision and context. For Qwen/Qwen3-8B converted to GGUF Q4_K_M, the simulator estimates 4.6 GiB for weights and 7.0 GiB in total with one user, an 8,192-token context, F16 KV cache, single-GPU llama.cpp CUDA buffers with flash attention and 5% headroom. Other 8B models can have different cache and runtime requirements. This is a planning estimate, not a measured allocation or a speed guarantee. Sources: Qwen3-8B official configuration.
An RTX 5090 has 32 GB of VRAM; llm4fun budgets 31.4 GiB as usable after its driver reservation. For meta-llama/Llama-3.3-70B-Instruct converted to GGUF Q4_K_M, the estimated weights alone take 39.7 GiB at 4.83 bits per weight. With one user, an 8,192-token context, F16 KV cache, llama.cpp CUDA runtime buffers with flash attention and 5% headroom, the total estimate is 45.3 GiB, so this configuration cannot fit fully on one card. CPU offload or a different quantization changes the memory and speed trade-offs; this is a planning calculation, not a measured run. Sources: NVIDIA RTX 5090 specifications; Meta Llama 3.3 model card.