NVIDIA · Consumer GPU
32 GB of GDDR7 on Blackwell. Check which quantized models fit the memory budget, then inspect speed and cost evidence for this variant.
Desktop 32 GB reference specification; laptop and regional D variants are separate.
Single-card inference · estimated
Q4_K_M weight files · FP16 KV cache · one request · 2 GiB runtime reserve. Context includes prompt and generated tokens.
3 of 4 sample models within the estimated budget at 4K context.
Within memory budget
22.56 GiB remaining
Qwen/Qwen3-8B-GGUF · revision 7c41481f57cb95916b40956ab2f0b139b296d974.
KV architecture source ↗: 36 layers, 8 KV heads, head dimension 128. Files checked 7 Nov 2026.
Within memory budget
18.79 GiB remaining
Qwen/Qwen3-14B-GGUF · revision 530227a7d994db8eca5ab5ced2fb692b614357fd.
KV architecture source ↗: 40 layers, 8 KV heads, head dimension 128. Files checked 7 Nov 2026.
Within memory budget
8.40 GiB remaining
Qwen/Qwen3-32B-GGUF · revision 938a7432affaec9157f883a87164e2646ae17555.
KV architecture source ↗: 64 layers, 8 KV heads, head dimension 128. Files checked 7 Nov 2026.
Over memory budget
13.05 GiB over the budget
bartowski/Llama-3.3-70B-Instruct-GGUF · revision b6c5c9f176f3279204034e1d16d393105e95cb88.
KV architecture source ↗: 80 layers, 8 KV heads, head dimension 128. Files checked 7 Nov 2026.
Exact quantized file bytes + FP16 KV cache + 2 GiB reserved for the runtime. KV bytes = 2 × layers × KV heads × head dimension × total context tokens × 2 bytes. 1 GiB = 2³⁰ bytes.
Nominal manufacturer GB labels use a conservative decimal-GB budget (1 GB = 10⁹ bytes). Actual free VRAM, engine allocation, driver and operating-system support must be checked. Passing this estimate does not establish a tested deployment or the largest model the card could run. CPU offload, multi-GPU and training are outside this calculation.
Published test evidence
Memory fit can help shortlist GeForce RTX 5090, but it does not establish output tokens per second. Validate your chosen model, quantization and engine before budgeting around its speed.
The context selector above changes memory estimates only. Published speed records keep their original model and test conditions; these are external reports, not our measurements.
Ownership cost
Historical official starting price announced 6 Jan 2025. Not a current retailer offer; board SKU, tax, shipping and availability vary.
Current purchase price and stock not verified. This is a historical reference, not a current seller quote.
Read the price announcement ↗Dated compute quotes
spot · GPU_INSTANCE · interruptible
Compute only. Storage and other fees are separate; confirm the current price and available capacity with the provider.
Full quote, configuration & evidence →spot · GPU_INSTANCE · interruptible
Compute only. Storage and other fees are separate; confirm the current price and available capacity with the provider.
Full quote, configuration & evidence →marketplace · GPU_INSTANCE
Compute only. Storage and other fees are separate; confirm the current price and available capacity with the provider.
Full quote, configuration & evidence →spot · GPU_INSTANCE · interruptible
Compute only. Storage and other fees are separate; confirm the current price and available capacity with the provider.
Full quote, configuration & evidence →marketplace · GPU_INSTANCE
Compute only. Storage and other fees are separate; confirm the current price and available capacity with the provider.
Full quote, configuration & evidence →marketplace · GPU_INSTANCE
Compute only. Storage and other fees are separate; confirm the current price and available capacity with the provider.
Full quote, configuration & evidence →marketplace · GPU_INSTANCE
Compute only. Storage and other fees are separate; confirm the current price and available capacity with the provider.
Full quote, configuration & evidence →marketplace · GPU_INSTANCE
Compute only. Storage and other fees are separate; confirm the current price and available capacity with the provider.
Full quote, configuration & evidence →marketplace · GPU_INSTANCE
Compute only. Storage and other fees are separate; confirm the current price and available capacity with the provider.
Full quote, configuration & evidence →marketplace · GPU_INSTANCE
Compute only. Storage and other fees are separate; confirm the current price and available capacity with the provider.
Full quote, configuration & evidence →marketplace · GPU_INSTANCE
Compute only. Storage and other fees are separate; confirm the current price and available capacity with the provider.
Full quote, configuration & evidence →marketplace · GPU_INSTANCE
Compute only. Storage and other fees are separate; confirm the current price and available capacity with the provider.
Full quote, configuration & evidence →marketplace · GPU_INSTANCE
Compute only. Storage and other fees are separate; confirm the current price and available capacity with the provider.
Full quote, configuration & evidence →marketplace · GPU_INSTANCE
Compute only. Storage and other fees are separate; confirm the current price and available capacity with the provider.
Full quote, configuration & evidence →marketplace · GPU_INSTANCE
Compute only. Storage and other fees are separate; confirm the current price and available capacity with the provider.
Full quote, configuration & evidence →spot · GPU_INSTANCE · interruptible
Compute only. Storage and other fees are separate; confirm the current price and available capacity with the provider.
Full quote, configuration & evidence →spot · GPU_INSTANCE · interruptible
Compute only. Storage and other fees are separate; confirm the current price and available capacity with the provider.
Full quote, configuration & evidence →marketplace · GPU_INSTANCE
Compute only. Storage and other fees are separate; confirm the current price and available capacity with the provider.
Full quote, configuration & evidence →marketplace · GPU_INSTANCE
Compute only. Storage and other fees are separate; confirm the current price and available capacity with the provider.
Full quote, configuration & evidence →marketplace · GPU_INSTANCE
Compute only. Storage and other fees are separate; confirm the current price and available capacity with the provider.
Full quote, configuration & evidence →marketplace · GPU_INSTANCE
Compute only. Storage and other fees are separate; confirm the current price and available capacity with the provider.
Full quote, configuration & evidence →spot · GPU_INSTANCE · interruptible
Compute only. Storage and other fees are separate; confirm the current price and available capacity with the provider.
Full quote, configuration & evidence →spot · GPU_INSTANCE · interruptible
Compute only. Storage and other fees are separate; confirm the current price and available capacity with the provider.
Full quote, configuration & evidence →marketplace · GPU_INSTANCE
Compute only. Storage and other fees are separate; confirm the current price and available capacity with the provider.
Full quote, configuration & evidence →spot · GPU_INSTANCE · interruptible
Compute only. Storage and other fees are separate; confirm the current price and available capacity with the provider.
Full quote, configuration & evidence →marketplace · GPU_INSTANCE
Compute only. Storage and other fees are separate; confirm the current price and available capacity with the provider.
Full quote, configuration & evidence →spot · GPU_INSTANCE · interruptible
Compute only. Storage and other fees are separate; confirm the current price and available capacity with the provider.
Full quote, configuration & evidence →marketplace · GPU_INSTANCE
Compute only. Storage and other fees are separate; confirm the current price and available capacity with the provider.
Full quote, configuration & evidence →spot · GPU_INSTANCE · interruptible
Compute only. Storage and other fees are separate; confirm the current price and available capacity with the provider.
Full quote, configuration & evidence →spot · GPU_INSTANCE · interruptible
Compute only. Storage and other fees are separate; confirm the current price and available capacity with the provider.
Full quote, configuration & evidence →marketplace · GPU_INSTANCE
Compute only. Storage and other fees are separate; confirm the current price and available capacity with the provider.
Full quote, configuration & evidence →marketplace · GPU_INSTANCE
Compute only. Storage and other fees are separate; confirm the current price and available capacity with the provider.
Full quote, configuration & evidence →marketplace · GPU_INSTANCE
Compute only. Storage and other fees are separate; confirm the current price and available capacity with the provider.
Full quote, configuration & evidence →marketplace · GPU_INSTANCE
Compute only. Storage and other fees are separate; confirm the current price and available capacity with the provider.
Full quote, configuration & evidence →marketplace · GPU_INSTANCE
Compute only. Storage and other fees are separate; confirm the current price and available capacity with the provider.
Full quote, configuration & evidence →spot · GPU_INSTANCE · interruptible
Compute only. Storage and other fees are separate; confirm the current price and available capacity with the provider.
Full quote, configuration & evidence →marketplace · GPU_INSTANCE
Compute only. Storage and other fees are separate; confirm the current price and available capacity with the provider.
Full quote, configuration & evidence →spot · GPU_INSTANCE · interruptible
Compute only. Storage and other fees are separate; confirm the current price and available capacity with the provider.
Full quote, configuration & evidence →spot · GPU_INSTANCE · interruptible
Compute only. Storage and other fees are separate; confirm the current price and available capacity with the provider.
Full quote, configuration & evidence →spot · GPU_INSTANCE · interruptible
Compute only. Storage and other fees are separate; confirm the current price and available capacity with the provider.
Full quote, configuration & evidence →marketplace · GPU_INSTANCE
Compute only. Storage and other fees are separate; confirm the current price and available capacity with the provider.
Full quote, configuration & evidence →marketplace · GPU_INSTANCE
Compute only. Storage and other fees are separate; confirm the current price and available capacity with the provider.
Full quote, configuration & evidence →spot · GPU_INSTANCE · interruptible
Compute only. Storage and other fees are separate; confirm the current price and available capacity with the provider.
Full quote, configuration & evidence →spot · GPU_INSTANCE · interruptible
Compute only. Storage and other fees are separate; confirm the current price and available capacity with the provider.
Full quote, configuration & evidence →spot · GPU_INSTANCE · interruptible
Compute only. Storage and other fees are separate; confirm the current price and available capacity with the provider.
Full quote, configuration & evidence →spot · GPU_INSTANCE · interruptible
Compute only. Storage and other fees are separate; confirm the current price and available capacity with the provider.
Full quote, configuration & evidence →Secure Cloud · Pod · non-interruptible
Compute only. Storage and other fees are separate; confirm the current price and available capacity with the provider.
Full quote, configuration & evidence →on-demand · GPU_INSTANCE · non-interruptible
Compute only. Storage and other fees are separate; confirm the current price and available capacity with the provider.
Full quote, configuration & evidence →This is the matching evidence currently in our catalog. It is not a complete provider comparison or a market-wide lowest-price claim.
Chip designer: NVIDIA. Desktop 32 GB reference specification; laptop and regional D variants are separate. Retail board brands, seller SKUs and regional availability need their own evidence.
Official hardware specifications ↗ · checked .
Model files and pinned revisions are attached to each memory estimate. Speed and price records link to their sources above. Rebuilding this page does not refresh those observation dates.
RDNA 4 · GDDR6
Intel · 24 GBXe2 · GDDR6
NVIDIA · 24 GBAmpere · GDDR6X
Compare Apple Silicon Macs and unified memory →
Compare buying, renting and API use with a workload budget →
