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
Intel · Intel GPUs · 2024
Intel Arc B580
Good budget option
12 GB with decent bandwidth for little money; software is the catch.
- Memory
- 12 GB
- Bandwidth
- 456 GB/s
- Power
- 190 W
- Largest popular model at 4-bit
- Gemma 4 12B
from $249 (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 | ≤ 411 tok/s | |
| Qwen3.5 9B | Runs | ≤ 80 tok/s | |
| Gemma 4 12B | Runs | ≤ 64 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.
- Arc B580 12 GB (any card)12 GBLaunch price: $249
- 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: Tinkerers on a tight budget.
Editorial opinionWould we buy it today?
Only if you enjoy tinkering; an RTX 3060 12 GB is simpler.
Pros and cons
Editorial opinionPros
- Low price
- 456 GB/s for 12 GB
Cons
- Fewer ready-made tools (SYCL, Vulkan)
- 12 GB
Specifications
Factual data- Manufacturer
- Intel
- Chip
- BMG-G21
- Architecture
- Xe2 (Battlemage)
- Type
- Graphics card
- Form factor
- PCIe card
- Released
- 2024
- Availability
- On sale
- Memory options
- 12 GB
- Memory type
- GDDR6
- Memory bus
- 192-bit
- Memory bandwidth
- 456 GB/s
- Usable for models (default)
- 12 GB / 12 GB
- Board / max power
- 190 W
- Interface
- PCIe 4.0 x8
- Compute stack
- SYCL / Vulkan
- Models
- Any model that fits
- Several units for one model
- No
Source: Manufacturer specifications
Software support
Editorial opinionHow well the popular local-AI tools run on it today (editorial assessment).
- llama.cppGood
- OllamaWorks with effort
- LM StudioGood
- vLLMWorks with effort
- 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
NVIDIA GPUs
NVIDIA GeForce RTX 3060 12 GB
- Memory
- 12 GB
- Bandwidth
- 360 GB/s
Largest popular model at 4-bit: Gemma 4 12B
The cheapest way into CUDA with 12 GB. Slow, but enough for 7–12B models.
from $329 (launch price)Good budget option
NVIDIA GPUs
NVIDIA GeForce RTX 5070 Ti
- Memory
- 16 GB
- Bandwidth
- 896 GB/s
Largest popular model at 4-bit: gpt-oss-20b
Nearly RTX 5080 bandwidth for less. Still 16 GB, so speed rather than size.
from $1,190 (typical price)Recommended