What is the largest model that fully fits under $3,000?

In this dataset that is Qwen2.5 72B at Q4, with an estimated memory need of 47.1 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 stored 3060, 3090 and 4090 prices are pcprice.watch used medians. Other rechecked GPU cards cite GPU PRIX or PriceSquirrel, and the 3090 and 4090 also show a GPU PRIX new price. Build totals add a sourced RAM line and 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.

budget

Local LLM under $3,000

Under $3,000 (€2,680 incl. VAT) localLLMrig picks Qwen2.5 72B 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 $3,000. The catalog compares against about €2,680 incl. VAT, an FX estimate.

Open in the calculator

Three setups

Qwen2.5 72B · Q4 · 8,192 ctx

Estimated memory

47.1 GBestimate

43.6 GB weights · 2.7 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.

01 · Fastest
Mac mini M4 Pro 64GB
Enough memory for 70B Q4, but bandwidth is modest. It fits; it is not fast.
$2,116€1,890
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
2.8
estimate
needed
47.1 GB
full fit
usable
54.0 GB
unified
Why this one
- The model fits entirely in VRAM or unified memory. No CPU offload.
- 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 Pro, 24 GB base configurable to 48 or 64 GB
- 273 GB/s according to Apple Support
EU shops
US shops are not linked yet.
02 · A step up
Mac Studio M5 Ultra 96GB
High bandwidth and enough memory for 70B Q4/Q5. FP16 70B does not fit.
$7,444€6,649
price as of 16 Oct 2026
Belgian Apple Store
Belgian Apple Store price for this config, from the 16 Oct 2026 fact-check.
over budget
tok/s estimate
12.4
estimate
needed
47.1 GB
full fit
usable
84.0 GB
unified
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.
- Unified memory: weights and KV cache share one pool.
- High memory bandwidth, so a higher tokens-per-second estimate.
- One box, little noise, no discrete GPU.
Parts
- Mac Studio M5 Ultra, 96 GB, 1.2 TB/s
EU shops
US shops are not linked yet.
03 · A step up
Mac Studio M5 Ultra 256GB
The machine in this list that can still hold 70B in FP16. The euro amount is an estimate.
$13,994€12,500
price as of 16 Oct 2026
price unverified
Estimate from the 16 Oct 2026 fact-check. Not a checked Apple Store listing. About €12,500–€13,000. This row stores the low end. 256 GB requires the 36-core CPU / 80-core GPU chip.
over budget
tok/s estimate
12.4
estimate
needed
47.1 GB
full fit
usable
244.0 GB
unified
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.
- Unified memory: weights and KV cache share one pool.
- High memory bandwidth, so a higher tokens-per-second estimate.
- One box, little noise, no discrete GPU.
Parts
- Mac Studio M5 Ultra, 256 GB unified memory, 1.2 TB/s
- 256 GB requires the 36-core CPU / 80-core GPU chip
EU shops
US shops are not linked yet.

With CPU offload, and therefore slower, this could also work: PC with Radeon RX 7900 XTX 24GB, ~1.6 tok/s estimate, $2,407€2,150.

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

Common questions

What is the largest model that fully fits under $3,000?: In this dataset that is Qwen2.5 72B at Q4, with an estimated memory need of 47.1 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 stored 3060, 3090 and 4090 prices are pcprice.watch used medians. Other rechecked GPU cards cite GPU PRIX or PriceSquirrel, and the 3090 and 4090 also show a GPU PRIX new price. Build totals add a sourced RAM line and 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 $3,000

Three setups

Mac mini M4 Pro 64GB

Mac Studio M5 Ultra 96GB

Mac Studio M5 Ultra 256GB

Get new builds when GPU prices move

Common questions