AMD GPU
AMD Radeon RX 7900 XT
The AMD Radeon RX 7900 XT has 20GB of VRAM and 800 GB/s of memory bandwidth. Its sweet spot tops out around Mistral-Small-24B-Instruct-2501 — the largest model that loads cleanly at a quality quant with llama.cpp at 8K context.
AMD verdicts are beta: fit is physics and holds, but ROCm/Vulkan speed tiers aren't calibrated yet — treat tiers as provisional until real measurements land.
- VRAM
- 20 GB
- Memory bandwidth
- 800 GB/s
- TDP
- 315 W
- MSRP
- $899
- Backends
- ROCm · Vulkan
Also good for gaming — 4K-class (estimated from FP32 compute, not a game benchmark)
Specs as of 2026-07-08 · source
AMD Radeon RX 7900 XT for local AI — common questions
- How much VRAM does the AMD Radeon RX 7900 XT have?
- The AMD Radeon RX 7900 XT has 20GB of VRAM with 800 GB/s of memory bandwidth. VRAM sets which models fit; bandwidth sets how fast they feel once they do.
- Is the AMD Radeon RX 7900 XT good for running AI models locally?
- Yes, within limits. 20GB comfortably runs small and mid-size models at a quality quant, but the largest open models will not fit. The largest model it loads cleanly is Mistral-Small-24B-Instruct-2501, at a quality quant with llama.cpp at 8K context.
- What runtimes work with the AMD Radeon RX 7900 XT?
- It runs on ROCm · Vulkan, which covers Ollama, llama.cpp and LM Studio. Runtime choice affects speed and features, not whether a model fits.
Affiliate link — we may earn a commission. Verdicts are computed before any link is attached.
What an AMD Radeon RX 7900 XT can run
Every model we track, graded at its best clean-fit quant. Click any verdict for the full breakdown.
Have a specific model in mind? Check it against the AMD Radeon RX 7900 XT at your own quant and context length.
Check with the AMD Radeon RX 7900 XT preselected →Verdicts computed from published specs and measured GGUF sizes — how the math works.