AMD GPUs
AMD Radeon RX 9060 XT 16 GB
- Memory
- 16 GB
- Bandwidth
- 320 GB/s
Largest popular model at 4-bit: gpt-oss-20b
The cheapest new 16 GB card. Slow memory, but it holds what an RTX 5060 Ti holds.
Intel · Intel GPUs · 2025
16 GB in a 70 W, low-profile card with no power cable: made for small servers.
from $349 (launch price)
Researched from manufacturer data and public sources; not tested by us.· Last reviewed Oct 11, 2026
Popular models at Q4_K_M with a 32K-token context. Memory needed from real model files; speed is the theoretical ceiling.
Model weightsContext cache (KV)RuntimeUsable limit (colour = verdict)
| Model | Verdict | Memory | Speed ceiling |
|---|---|---|---|
| Qwen3 1.7B | Runs | ≤ 202 tok/s | |
| Qwen3.5 9B | Runs | ≤ 39 tok/s | |
| Gemma 4 12B | Runs | ≤ 31 tok/s | |
| gpt-oss-20b | Runs | ≤ 112 tok/s | |
| Qwen3.6 27B | Not enough memory | — | |
| Qwen3.6 35B A3B | Partly in system RAM | — | |
| Llama 3.3 70B | Not enough memory | — | |
| gpt-oss-120b | Partly in system RAM | — | |
| Qwen3.5 122B A10B | Partly in system RAM | — | |
| Qwen3.5 397B A17B | Partly in system RAM | — |
Theoretical maximum for generating text: memory bandwidth divided by the bytes read per token. Real runs usually reach about half to three quarters of it.
Prices are editorial references (launch price and a typical street price on the date shown), not live prices. In 2026 the memory shortage has pushed many prices well above launch.
Prices are shown only if updated in the last 24 hours and may change; the retailer’s price at checkout applies. We may earn a commission from these links at no cost to you. Affiliate disclosure
Best for: Mini towers and NAS boxes where a big card will not fit.
Yes for tiny or low-power servers; anywhere else a faster card is better value.
Source: Manufacturer specifications
How well the popular local-AI tools run on it today (editorial assessment).
Measured results with their source. We never invent speeds.
No measured results yet. The table above shows the theoretical ceiling instead.
AMD GPUs
Largest popular model at 4-bit: gpt-oss-20b
The cheapest new 16 GB card. Slow memory, but it holds what an RTX 5060 Ti holds.

NVIDIA GPUs
Largest popular model at 4-bit: Gemma 4 12B
The cheapest way into CUDA with 12 GB. Slow, but enough for 7–12B models.
NVIDIA GPUs
Largest popular model at 4-bit: Qwen3.6 27B
24 GB in a single-slot, 140 W card: the homelab-friendly way to get 24 GB new.