# Radeon RX 7900 XTX for local AI

URL: https://insidethemachine.ai/machines/radeon-rx-7900-xtx
Type: AMD graphics card. Chip: Navi 31. Memory: vram, options 24 GB. Bandwidth: 960 GB/s. Spec source: https://en.wikipedia.org/wiki/List_of_AMD_graphics_processing_units (2026-10-15).
Price: from about $950 (2026-10-02, approximate). Status: previous_gen.

## Which models fit

| memory GB | usable GB | models that fit | best 3 |
|---|---|---|---|
| 24 | 23 | 56 | Qwen3.8 27B (22.7 GB), Qwen3.5 27B (21.5 GB), Qwen3.6 27B (21.5 GB) |

## Published speeds

None found yet.

Notes: ROCm + Vulkan in llama.cpp. 24GB at ~$950 used.

## Questions

**What is the best local LLM for the Radeon RX 7900 XTX?**
With 24 GB, Qwen3.8 27B (needs 22.7 GB, AA 33.7). 56 of 124 models fit.

**How much does the Radeon RX 7900 XTX cost?**
From about $950 (as of 2026-10-02). 2026 prices are inflated by the memory-chip shortage; check before buying.