NVIDIA · NVIDIA GPUs · 2025
Fast, but only 16 GB: the same memory as cards that cost a third as much.
from $1,830 (typical 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 | ≤ 865 tok/s | |
| Qwen3.5 9B | Runs | ≤ 169 tok/s | |
| Gemma 4 12B | Runs | ≤ 135 tok/s | |
| gpt-oss-20b | Runs | ≤ 480 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: Gamers who also run small models; not a good buy for AI alone.
No for AI. An RTX 5060 Ti 16 GB holds the same models for far less, or a 24–32 GB card holds more.
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.
NVIDIA GPUs
Largest popular model at 4-bit: gpt-oss-20b
The cheapest new NVIDIA card with 16 GB. Low power and CUDA make it the easy starter card.
Same 16 GB for far less
NVIDIA GPUs
Largest popular model at 4-bit: Qwen3.6 27B
The homelab classic: 24 GB and 936 GB/s, bought used. Two of them make 48 GB.
24 GB for a similar price