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 · 2025
24 GB in a single-slot, 140 W card: the homelab-friendly way to get 24 GB new.
from $1,500 (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 | ≤ 605 tok/s | |
| Qwen3.5 9B | Runs | ≤ 118 tok/s | |
| Gemma 4 12B | Runs | ≤ 94 tok/s | |
| gpt-oss-20b | Runs | ≤ 336 tok/s | |
| Qwen3.6 27B | Runs | ≤ 40 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.
An SFF edition (low profile, lower power) also exists.
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: Small servers, several cards side by side, and quiet always-on boxes.
Yes if space, power or warranty matter more than raw speed.
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.