NVIDIA GPUs
NVIDIA RTX PRO 4000 Blackwell
- Memory
- 24 GB
- Bandwidth
- 672 GB/s
Largest popular model at 4-bit: Qwen3.6 27B
24 GB in a single-slot, 140 W card: the homelab-friendly way to get 24 GB new.
from $1,500 (typical price)Recommended
AMD · AMD GPUs · 2022
AMD Radeon RX 7900 XTX
Photo: Geni · CC BY-SA 4.0
Recommended
24 GB and 960 GB/s: RTX 3090-class memory, bought new.
- Memory
- 24 GB
- Bandwidth
- 960 GB/s
- Power
- 355 W
- Largest popular model at 4-bit
- Qwen3.6 27B
from $1,358 (typical 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 | ≤ 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 | Runs | ≤ 57 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.
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.
- RX 7900 XTX 24 GB (any partner card)24 GBLaunch price: $999 · Typical price: ~$1,358 (checked Oct 10, 2026)
- 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 new 24 GB card for Linux users who do not need CUDA.
Editorial opinionWould we buy it today?
Good if you want 24 GB new and avoid the used market.
Pros and cons
Editorial opinionPros
- 24 GB new with warranty
- Fast memory
Cons
- 355 W
- ROCm support for RDNA 3 is good but not CUDA-level
Specifications
Factual data- Manufacturer
- AMD
- Chip
- Navi 31
- Architecture
- RDNA 3
- Type
- Graphics card
- Form factor
- PCIe card
- Released
- 2022
- Availability
- On sale
- Memory options
- 24 GB
- Memory type
- GDDR6
- Memory bus
- 384-bit
- Memory bandwidth
- 960 GB/s
- Usable for models (default)
- 24 GB / 24 GB
- Board / max power
- 355 W
- Interface
- PCIe 4.0 x16
- Power connector
- 2× 8-pin
- Compute stack
- ROCm / Vulkan
- 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.cppGood
- OllamaGood
- 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
Intel GPUs
Intel Arc Pro B70
- Memory
- 32 GB
- Bandwidth
- 608 GB/s
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.
from $1,268 (typical price)Recommended
NVIDIA GPUs
NVIDIA GeForce RTX 3090
- Memory
- 24 GB
- Bandwidth
- 936 GB/s
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.
from $1,340 (typical price)Good budget option