Best local LLM setup under £500 for coding (2026)

Used office tower + Tesla P40 24GB

£340–£465

runs Qwen2.5-Coder-32B-Instruct Q4_K_M

no published benchmark yet

Qwen2.5-Coder-32B-Instruct Q4_K_M for around £403 — the best coding value at this budget

This is a noisy, fiddly, enthusiast build — not for someone who wants it to 'just work'
Corporate towers (Dell OptiPlex, HP EliteDesk/ProDesk) often ship with proprietary or low-wattage PSUs — check for a free PCIe x16 slot, physical case clearance, and budget for a replacement 750W PSU before buying a GPU for it
Passive cooling only — no fan. You must fit a 3D-printed shroud and a high-static-pressure fan or it will thermal-throttle
No video output at all — you need a second GPU or the host's onboard/iGPU video for a display
Requires 'Above 4G Decoding' / Re-Size BAR enabled in the host BIOS to be recognised correctly
Pascal architecture with no Tensor Cores — markedly slower than a same-VRAM RTX card, so pin your driver/CUDA versions and avoid bleeding-edge llama.cpp builds that assume newer GPUs
Draws ~250W continuously under load — a real electricity cost if left on
Buy new, not used, and confirm it has enough spare 8-pin PCIe power connectors for the GPU you're pairing it with — a failing or underpowered PSU can take a used GPU down with it

Prices checked: 2026-08-26

How to put it together

Enable 'Above 4G Decoding' / Re-Size BAR in the motherboard BIOS before installing the card
3D-print (or buy printed) a P40 fan shroud and fit a high-static-pressure 40-92mm fan to it
Fit the 750W PSU and connect the two 8-pin EPS/PCIe power leads the P40 needs (check your specific card's power connector — some use CPU EPS connectors via an adapter)
Seat the P40 in the primary PCIe x16 slot; keep the onboard/iGPU video output connected for the display
Install the datacentre driver branch for Pascal and pin that driver version — avoid unattended driver upgrades
Install llama.cpp with CUDA support and load a Q4_K_M model to confirm GPU offload and check temperatures under load

Confirm the fan shroud fan is powered from a fan header or molex before first boot — running the card without airflow for even a few minutes under load risks thermal throttling or damage

£325–£420

runs Qwen2.5-Coder-14B-Instruct Q4_K_M

no published benchmark yet

Qwen2.5-Coder-14B-Instruct Q4_K_M for around £373 — a strong coding option at this budget

Limited to models that comfortably fit in 12GB VRAM (roughly 8B-class at Q4)
Cheapest way into a usable local chat rig as of August 2026
Corporate towers (Dell OptiPlex, HP EliteDesk/ProDesk) often ship with proprietary or low-wattage PSUs — check for a free PCIe x16 slot, physical case clearance, and budget for a replacement 750W PSU before buying a GPU for it
Needs a PSU with a free 8-pin PCIe connector
Plain GDDR6 (not GDDR6X) has kept this card largely insulated from the 2026 memory-chip shortage — currently the best £/VRAM entry point
Buy new, not used, and confirm it has enough spare 8-pin PCIe power connectors for the GPU you're pairing it with — a failing or underpowered PSU can take a used GPU down with it

Prices checked: 2026-08-26

How to put it together

Open the tower side panel and check for a free PCIe x16 slot and an 8-pin PCIe power lead
Fit the 750W PSU if the stock one lacks an 8-pin PCIe connector, wiring the 24-pin motherboard and CPU 8-pin
Seat the RTX 3060 in the primary PCIe x16 slot and connect the 8-pin PCIe cable
Boot into the OS and install the latest NVIDIA driver
Install Ollama or llama.cpp and pull a Q4_K_M model to confirm it loads onto the GPU

Office towers with a proprietary (e.g. SFX or low-wattage) PSU won't have a spare PCIe power lead — check before assuming the stock PSU is enough