New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
AMD Radeon RX 7900 XT
Runs downloadable LLMs up to ~26B at Q4, ~112.5-137.5 tok/s on an 8B model.
What you can run
At 8k context, FP16 KV. Full-speed tok/s holds up to "max ctx"; beyond it the context spills to system RAM (CPU/PCIe offload) and drops to the degraded figure.
| Model size | FP16 | Q8 | Q4 |
|---|---|---|---|
| 3B |
84-102.7 t/s ≤166k ctx · then ~4.2-5.1 (slow) |
168-205.3 t/s ≤212k ctx · then ~8.4-10.3 (slow) |
300-366.7 t/s ≤232k ctx · then ~15-18.3 (slow) |
| 7-8B |
31.5-38.5 t/s ≤7k ctx · then ~1.6-1.9 (slow) |
63-77 t/s ≤68k ctx · then ~3.2-3.9 (slow) |
112.5-137.5 t/s ≤95k ctx · then ~5.6-6.9 (slow) |
| 13B | won't run |
38.8-47.4 t/s ≤24k ctx · then ~1.9-2.4 (slow) |
69.2-84.6 t/s ≤59k ctx · then ~3.5-4.2 (slow) |
| 32B | won't run | won't run | won't run |
| 70B | won't run | won't run | won't run |
| 120B | won't run | won't run | won't run |
| 400B | won't run | won't run | won't run |
Estimate: tok/s ≈ bandwidth ÷ (params × bytes/param) × efficiency (AMD). Cyan = fits ~18.4 GB usable. Beyond "ctx", KV spills to system RAM (CPU/PCIe offload) (rough degraded speed shown).
What else you need for a full build▶
Minimum supporting components for a desktop built around the AMD Radeon RX 7900 XT. Guidance — exact needs depend on your case, other parts and how much you offload to system RAM.
Run popular models on the AMD Radeon RX 7900 XT
Videos about the AMD Radeon RX 7900 XT
The Cheapest* AMD RX 7900 XT: Revisit Benchmarks, & Price Drops vs. 4070 Ti & More
Radeon RX 7900 XT Re-Review, What Should Have Been!
More hardware like the AMD Radeon RX 7900 XT
About the AMD Radeon RX 7900 XT
AMD Radeon RX 7900 XT is a discrete GPU from AMD on RDNA 3, 2022. For local genAI the numbers that matter are its 20 GB (how big a model + context fits) and 800 GB/s bandwidth (generation speed). Plan for a ~750W power supply.
Frequently asked questions
What size LLM can the AMD Radeon RX 7900 XT run?▶
With ~18.4 GB usable it runs up to ~26B at Q4 (~7.5B at FP16) at 8k context. Bigger spills into system RAM (CPU/PCIe offload) and slows sharply.
How many tokens/sec does the AMD Radeon RX 7900 XT generate?▶
Generation is bandwidth-bound. At 800 GB/s an 8B model at Q4 runs ~112.5-137.5 tok/s (estimate).
Why does long context slow it down?▶
The KV cache for the context must also fit fast memory; once weights+KV exceed 18.4 GB it spills to system RAM (CPU/PCIe offload) and throughput collapses. Each row shows the max usable context.
What else do I need to run the AMD Radeon RX 7900 XT?▶
Besides the card: a ≥750W 80+ Gold power supply, at least 20GB of system RAM (2× the 20GB VRAM is ideal for CPU offload), a free PCIe x16 slot, any modern multi-core CPU, and a ≥1TB NVMe SSD for model weights.