localLLMriglocal, on your table

budget

Local LLM under $800

Under $800 (€715 incl. VAT) localLLMrig picks Gemma 2 9B at Q4 as the largest model that fully fits somewhere. Global prices (USD), EUR available. Those prices are marked price unverified. Tokens/s are estimates.

This page is $800. The catalog compares against about €715 incl. VAT, an FX estimate.

Open in the calculator

Three setups

Gemma 2 9B · Q4 · 8,192 ctx

Estimated memory

8.5 GBestimate

5.5 GB weights · 2.1 GB KV cache · 0.8 GB overhead

You didn't pick a model. Inside this budget, this is the largest model that fully fits somewhere.

  1. 01 · Fastest

    Mac mini M4 16GB

    Quiet and cheap for 8B Q4. Not for 32B or 70B.

    $615€549

    price as of 16 Oct 2026

    price unverified

    Used-market euro amount from the earlier catalog. It cannot be checked on the Apple Store.

    inside budget · used

    tok/s estimate

    7.5

    estimate

    needed

    8.5 GB

    full fit

    usable

    10.0 GB

    unified

    Why this one

    • The model fits entirely in VRAM or unified memory. No CPU offload.
    • It fits, with little room left. A longer context can push it over.
    • The indicative price is inside your budget.
    • Unified memory: weights and KV cache share one pool.
    • Second-hand or a previous generation. The price moves around.
    • One box, little noise, no discrete GPU.
    • Highest estimated speed in this shortlist.

    Parts

    • Mac mini (2024) M4, 16 GB unified memory, configurable to 24 or 32 GB
    • 120 GB/s according to Apple Support

  2. 02 · A step up

    PC with RTX 5090 32GB

    Highest bandwidth in a single card. 32 GB is plenty for 32B, still too tight for 70B Q4.

    $8,955€7,999

    price as of 16 Oct 2026

    rest of system (estimate): $1,903€1,700. The total is that estimate plus the sourced GPU price. It is not a checked system price.

    price unverified

    GPU line is the €6,299 PriceSquirrel in-stock floor at Proshop (FI) (https://www.pricesquirrel.com/gpus/rtx-5090). Rest of system (estimate) €1,700. The rest is the previous catalog gap, the old build total minus the old card price. It was not rechecked on 16 Oct 2026. The total is that estimate plus the sourced GPU price. It is not a checked system price.

    over budget

    tok/s estimate

    176

    estimate

    needed

    8.5 GB

    full fit

    usable

    31.4 GB

    VRAM

    Why this one

    • The model fits entirely in VRAM or unified memory. No CPU offload.
    • Memory left for a longer context or a heavier quantisation.
    • Above your budget. Nothing fully fit inside the amount, or this is a faster step above it.
    • High memory bandwidth, so a higher tokens-per-second estimate.

    Parts

    • GeForce RTX 5090 32GB
    • Rest of system (estimate): €1,700. Not a checked listing.
    • Ryzen 7 9700X or similar
    • 96 GB DDR5
    • 1200W PSU, roomy case

  3. 03 · A step up

    Dual RTX 4090, 48 GB

    Same memory as two 3090s, higher bandwidth, a lot more money.

    $10,490€9,370

    price as of 16 Oct 2026

    rest of system (estimate): $2,004€1,790. The total is that estimate plus the sourced GPU price. It is not a checked system price.

    price unverified

    GPU line is 2× the GPU PRIX current low €3,790 (€7,580, https://gpuprix.com/eu/gpus/geforce-rtx-4090). Rest of system (estimate) €1,790. The rest is the previous catalog gap, the old build total minus the old card price. It was not rechecked on 16 Oct 2026. The total is that estimate plus the sourced GPU price. It is not a checked system price.

    over budget

    tok/s estimate

    110

    estimate

    needed

    8.5 GB

    full fit

    usable

    46.8 GB

    VRAM

    Why this one

    • The model fits entirely in VRAM or unified memory. No CPU offload.
    • Memory left for a longer context or a heavier quantisation.
    • Above your budget. Nothing fully fit inside the amount, or this is a faster step above it.
    • Two GPUs. Expect a heavier PSU and a llama.cpp split. Bandwidth does not fully double.
    • High memory bandwidth, so a higher tokens-per-second estimate.

    Parts

    • 2× GeForce RTX 4090 24GB
    • Rest of system (estimate): €1,790. Not a checked listing.
    • Ryzen 9 7950X or similar
    • 128 GB DDR5
    • 1600W PSU

Tokens per second are estimated from memory bandwidth, not from a measured benchmark. EUR prices include VAT. USD is an FX estimate. A price without a checked listing is marked price unverified. Run llama-bench yourself before you buy.

Want a build tailored to you? Custom report

Get new builds when GPU prices move

End of results

Common questions

What is the largest model that fully fits under $800?
In this dataset that is Gemma 2 9B at Q4, with an estimated memory need of 8.5 GB at 8,192 tokens. That is an estimate. sourceUrl stays null.
Is a 70B model always included?
No. Llama 70B Q4_K_M needs about 42 GB of weights, about 46 GB with KV cache and overhead at 8,192 tokens. At the lower amounts it does not fully fit. The page then shows a smaller model that does, or the fastest full fits above the budget when nothing inside it does.
Are the prices shop prices?
The rechecked GPU cards cite GPU PRIX or PriceSquirrel. Build totals add rest of system (estimate) and stay unverified. Three Apple configs cite the Belgian Apple Store. Other Apple euro amounts are estimates or used figures. EUR includes VAT. USD is an FX estimate.
Local LLM under $800 · localLLMrig