§01·compatibility · /check
Qwen2.5 14B on RX 7900 XTX
Yes — Qwen2.5 14B runs on the RX 7900 XTX (24 GB). Fastest community-measured result: 32 tokens/s, with 24 GB peak VRAM.
✓ runsllmactiveamd series24GB VRAM
step-by-step recipe for this pair
Qwen2.5-14B-Instruct on RX 7900 XTX: a fast local chat LLM via Ollama (ROCm)
llmbeginner9GB+
§02·benchmarks
| Task | Quant | Speed | VRAM | Works | Confidence | Source | Verified |
|---|---|---|---|---|---|---|---|
| llm | Q4_K - Medium | 32tokens/s | 24GB | ✓ | localscore.ai· web | 2026-05-15 |
§03·common questions
Can you run Qwen2.5 14B on RX 7900 XTX?
Yes — Qwen2.5 14B runs on the RX 7900 XTX (24 GB). Fastest community-measured result: 32 tokens/s, with 24 GB peak VRAM.
How much VRAM does Qwen2.5 14B need on RX 7900 XTX?
Measured peak VRAM is 24 GB.
Which quantizations have been tested for Qwen2.5 14B on RX 7900 XTX?
Q4_K - Medium — measured in community benchmarks.
How fast is Qwen2.5 14B on RX 7900 XTX?
Up to 32 tokens/s (llm), the fastest community-measured result.
Are there step-by-step instructions for Qwen2.5 14B on RX 7900 XTX?
Yes — a step-by-step recipe documents Qwen2.5 14B on the RX 7900 XTX, linked at the top of this page.