AMD GPUs
AMD Radeon AI PRO R9700
- Memory
- 32 GB
- Bandwidth
- 645 GB/s
Largest popular model at 4-bit: Qwen3.6 35B A3B
32 GB for about a third of an RTX 5090: the cheapest new 32 GB card.
NVIDIA · NVIDIA GPUs · 2020
The homelab classic: 24 GB and 936 GB/s, bought used. Two of them make 48 GB.
from $1,340 (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 | ≤ 843 tok/s | |
| Qwen3.5 9B | Runs | ≤ 165 tok/s | |
| Gemma 4 12B | Runs | ≤ 131 tok/s | |
| gpt-oss-20b | Runs | ≤ 468 tok/s | |
| Qwen3.6 27B | Runs | ≤ 56 tok/s | |
| 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.
Second-hand: prefer renewed units with a warranty; check that the memory pads and fans are in good shape.
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: 24 GB on a budget, and 48 GB builds with two cards for 70B models.
Yes, from a seller with a warranty. Still the best value per GB of fast GPU memory.
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: Qwen3.6 35B A3B
32 GB for about a third of an RTX 5090: the cheapest new 32 GB card.

AMD GPUs
Largest popular model at 4-bit: Qwen3.6 27B
24 GB and 960 GB/s: RTX 3090-class memory, bought new.
Intel GPUs
Largest popular model at 4-bit: Qwen3.6 35B A3B
Intel's big Battlemage: 32 GB and 608 GB/s for less than AMD's R9700.