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.
from $349 (launch price)Good budget option
NVIDIA · NVIDIA GPUs · 2021
NVIDIA GeForce RTX 3060 12 GB
Photo: Qurren · CC BY-SA 4.0
Good budget option
The cheapest way into CUDA with 12 GB. Slow, but enough for 7–12B models.
- Memory
- 12 GB
- Bandwidth
- 360 GB/s
- Power
- 170 W
- Largest popular model at 4-bit
- Gemma 4 12B
from $329 (launch price)
Researched from manufacturer data and public sources; not tested by us.· Last reviewed Oct 11, 2026
What it can run
EstimatePopular models at Q4_K_M with a 32K-token context. Memory needed from real model files; speed is the theoretical ceiling.
Change model size or context
Model weightsContext cache (KV)RuntimeUsable limit (colour = verdict)
| Model | Verdict | Memory | Speed ceiling |
|---|---|---|---|
| Qwen3 1.7B | Runs | ≤ 324 tok/s | |
| Qwen3.5 9B | Runs | ≤ 63 tok/s | |
| Gemma 4 12B | Runs | ≤ 51 tok/s | |
| gpt-oss-20b | Partly in system RAM | — | |
| 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.
Where to buy
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.
- RTX 3060 12 GB (any partner card)12 GBLaunch price: $329
Avoid the 8 GB version.
- Check price Amazon.com (opens in a new tab)Amazon.comCheck availability
Other regions (3)
- Check price Amazon.co.uk (opens in a new tab)Amazon.co.ukUnited Kingdom · Check availability · Search results
- Check price Amazon.es (opens in a new tab)Amazon.esSpain · Check availability
- Check price Amazon.de (opens in a new tab)Amazon.deGermany · Check availability · Search results
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
Overview
Editorial opinionBest for: A low-cost card for Home Assistant voice, small chat models and learning.
Editorial opinionWould we buy it today?
Yes for a small, cheap assistant server; for more headroom go to 16 GB.
Pros and cons
Editorial opinionPros
- Low price for 12 GB with CUDA
- 170 W, one power connector
Cons
- 360 GB/s: modest speed
- 12 GB limits model choice
Specifications
Factual data- Manufacturer
- NVIDIA
- Chip
- GA106
- Architecture
- Ampere
- Type
- Graphics card
- Form factor
- PCIe card
- Released
- 2021
- Availability
- On sale
- Memory options
- 12 GB
- Memory type
- GDDR6
- Memory bus
- 192-bit
- Memory bandwidth
- 360 GB/s
- Usable for models (default)
- 12 GB / 12 GB
- Board / max power
- 170 W
- Interface
- PCIe 4.0 x16
- Power connector
- 8-pin
- Compute stack
- CUDA
- Models
- Any model that fits
- Several units for one model
- Yes
Source: Manufacturer specifications
Software support
Editorial opinionHow well the popular local-AI tools run on it today (editorial assessment).
- llama.cppExcellent
- OllamaExcellent
- LM StudioExcellent
- vLLMExcellent
- MLXNot supported
Measured speeds
Factual dataMeasured results with their source. We never invent speeds.
No measured results yet. The table above shows the theoretical ceiling instead.
Alternatives
Intel GPUs
Intel Arc Pro B50
- Memory
- 16 GB
- Bandwidth
- 224 GB/s
Largest popular model at 4-bit: gpt-oss-20b
16 GB in a 70 W, low-profile card with no power cable: made for small servers.
from $349 (launch price)Good budget option
Intel GPUs
Intel Arc B580
- Memory
- 12 GB
- Bandwidth
- 456 GB/s
Largest popular model at 4-bit: Gemma 4 12B
12 GB with decent bandwidth for little money; software is the catch.
from $249 (launch price)Good budget option