CUSTOMYOURPC
Log In | Register US United States Change region
Toggle dark mode

PC builds for Qwen2.5-Coder 32B

A minimum build, the one we'd recommend, and a max-performance build — every part chosen for technical fit and checked for compatibility.

Hardware requirement

Estimated

Running Qwen2.5-Coder 32B as Q4_K_M in Ollama at ~16,384 tokens of context.

VRAM to run on GPU
24 GB
32 GB class card
System RAM
32 GB
recommended
Storage
2 TB
NVMe recommended
GPU importance
Critical
memory-bound workload
How this is calculated
Model weights
derived
19 GB 32.764 billion parameters × 0.58 bytes/param (Q4_K_M) ≈ 19.0 GB.
KV cache (context memory)
derived
4.3 GB 16,384 tokens × 64 layers × 2 × 8 KV heads × 128 head dim × 2 bytes ≈ 4.3 GB. Grows with context length.
Runtime overhead
estimate
1 GB Fixed VRAM overhead for Ollama (activations, CUDA context, fragmentation headroom).
Total VRAM to run fully on GPU
estimate
24.3 GB Weights + KV cache + overhead. This is what you need to keep the whole model on the graphics card for full speed.
Recommended system RAM
estimate
32 GB Headroom to load the model, run the OS, and hold any layers offloaded from the GPU. Rounded up to a standard kit size.
Storage
estimate
2 TB NVMe recommended Local model files are large (often tens of GB each). An NVMe SSD keeps load times reasonable.

Memory figures are estimates derived from published model facts using a fixed method. They are not benchmarks. We do not publish tokens-per-second figures because we have no measured source for them.

Recommended builds

Minimum

"It runs."

$1,459 reference total

Runs Qwen2.5-Coder 32B (Q4_K_M) in Ollama fully on the GPU at ~8K context.

GPU VRAM
24 GB
Est. draw
528 W
PSU headroom
42%
Compatibility: Compatible
  • This model needs about 22 GB of VRAM under lean settings. The GeForce RTX 3090 Founders Edition (24 GB) is the most affordable card that holds the whole model on the GPU.

  • Processor
    AMD Ryzen 5 5600X
    $130

    Local AI inference runs on the GPU, so a capable budget CPU like the AMD Ryzen 5 5600X keeps costs down without holding the model back.

  • Motherboard
    Gigabyte B550M DS3H
    $100

    Matches the CPU socket (AM4) and DDR4 memory; a solid value board with room to expand.

  • This model wants about 32 GB of system RAM; the 32 GB DDR4 kit covers it with headroom for the OS and offload.

  • Storage
    Crucial P3 Plus
    $62

    1 TB of NVMe — local model files are large (tens of GB each), and NVMe keeps load times short.

  • Keeps the CPU cool and quiet under sustained load; compatible with the chosen socket.

  • Power Supply
    MSI MAG A750GL PCIE5
    $110

    Estimated system draw is about 528 W; the 750 W unit leaves headroom for GPU power spikes and efficiency.

  • Fits the motherboard form factor and has clearance for the graphics card (360 mm).

Recommended

Your pick

"The build we would buy."

$3,032 reference total

Runs Qwen2.5-Coder 32B (Q4_K_M) in Ollama fully on the GPU at ~16K context.

GPU VRAM
32 GB
Est. draw
798 W
PSU headroom
50%
Compatibility: Compatible
  • $2,000

    This model needs about 24 GB of VRAM. The GeForce RTX 5090 Founders Edition (32 GB) holds it with comfortable headroom for longer context and running other apps alongside it.

  • Processor
    AMD Ryzen 5 7600X
    $201

    The AMD Ryzen 5 7600X is a modern DDR5 platform — plenty for feeding the GPU, prompt processing, and everyday work, with an upgrade path.

  • Matches the CPU socket (AM5) and DDR5 memory; a solid value board with room to expand.

  • This model wants about 32 GB of system RAM; the 32 GB DDR5 kit covers it with headroom for the OS and offload.

  • Storage
    Samsung 990 Pro
    $170

    2 TB of NVMe — local model files are large (tens of GB each), and NVMe keeps load times short.

  • Keeps the CPU cool and quiet under sustained load; compatible with the chosen socket.

  • Power Supply
    Corsair HX1200 (2023)
    $250

    Estimated system draw is about 798 W; the 1200 W unit leaves headroom for GPU power spikes and efficiency.

  • Fits the motherboard form factor and has clearance for the graphics card (360 mm).

Max performance

"For users who value performance over budget."

$3,478 reference total

Runs Qwen2.5-Coder 32B (Q4_K_M) in Ollama fully on the GPU at ~16K context.

GPU VRAM
32 GB
Est. draw
823 W
PSU headroom
46%
Compatibility: Compatible
  • $2,000

    The most VRAM available here (32 GB) — maximum context and headroom, well above the ~24 GB this model needs.

  • $472

    The AMD Ryzen 7 9800X3D handles heavy multitasking, data prep, and CPU-side tokenization alongside a top GPU.

  • Matches the CPU socket (AM5) and DDR5 memory; a solid value board with room to expand.

  • This model wants about 32 GB of system RAM; the 32 GB DDR5 kit covers it with headroom for the OS and offload.

  • Storage
    Samsung 990 Pro
    $170

    2 TB of NVMe — local model files are large (tens of GB each), and NVMe keeps load times short.

  • Keeps the CPU cool and quiet under sustained load; compatible with the chosen socket.

  • Power Supply
    Corsair HX1200 (2023)
    $250

    Estimated system draw is about 823 W; the 1200 W unit leaves headroom for GPU power spikes and efficiency.

  • Fits the motherboard form factor and has clearance for the graphics card (435 mm).

Totals are the sum of current reference prices for each part, not live retailer pricing. Component choices are made purely on technical fit. We may earn a commission when you buy through links on this site. It never changes the price you pay, and it never affects which hardware we recommend. Learn more.