AMD RX 7900 XTX - 24GB usable

Specifications

BrandAMD
ModelRX 7900 XTX
Usable VRAM24GB
ArchitectureRDNA3
CUDA / Stream Processors6,144
Memory Bandwidth960 GB/s
TDP355W
FP32 TFLOPS61

Current Offers

Used from £1,000

Prices last updated:

GPUDojo is reader-supported. When you buy through links on our site, we may earn an affiliate commission.

Lowest tracked offers by retailer

UK · GBP · Weekly since Aug 2026 · Shipping may be extra

£750£1,000£1,250£1,500Aug 21Sep 8Sep 27Oct 15Nov 3eBay £1,000
About these prices

Each line is the lowest offer we tracked from that retailer at weekly snapshots, ending at today's offer. The condition can vary between snapshots (new, used, or unrecorded for older ones). eBay prices exclude shipping.

Weekly offers table
Lowest tracked offer per retailer · UK · GBP
DateeBay
Today, Nov 3, 2026 £999.95
Oct 30, 2026 £899.00
Oct 23, 2026 £780.00
Oct 9, 2026 £779.00
Oct 2, 2026 £779.00
Sep 25, 2026 £767.37
Sep 18, 2026 £843.10
Sep 11, 2026 £792.10
Sep 4, 2026 £868.60
Sep 1, 2026 £1,447.87
Aug 28, 2026 £873.70
Aug 21, 2026 £750.00

For AI / LLM Use

Solid choice for 30B models and comfortable 14B inference. Verify ROCm support for the exact framework and operating system you plan to use.

What Models Can It Run?

  • 30B Q4_K_M, 14B full precision, 70B Q2 (tight)
  • 14B Q6_K, 30B Q3_K (tight)
  • 14B Q4_K_M, 7B full precision
  • 7B Q6_K, 14B Q3_K (tight)
  • 7B Q4_K_M only

Estimated Performance

Generation: ~72 tokens/sec

Prefill: ~1089 tokens/sec

Recommended Quantisations

  • Q4_K_M recommended for 30B models
  • Q6_K or Q8 for 14B and below
  • Full precision for 7B

Pros & Cons

Pros

  • 24GB usable VRAM: handles large models
  • High memory bandwidth for fast generation
  • RDNA3 architecture: supported by current ROCm stacks
  • Consumer card: easy to install, display output

Cons

  • 355W TDP: high power draw
  • ROCm and CUDA-first framework compatibility should be checked before purchase

Community Verdict

No community reviews yet for the RX 7900 XTX. Know a good review? Let us know.