GPU comparison
NVIDIA RTX 4080 (16GB) vs NVIDIA RTX Pro 6000 Blackwell (96GB) for local LLMs
How the two stack up for running open-source LLMs locally — memory, bandwidth, price, and how many of the 48 tracked models each one can run.
| NVIDIA RTX 4080 (16GB) | NVIDIA RTX Pro 6000 Blackwell (96GB) | |
|---|---|---|
| Memory | 16.0 GB | 96.0 GB |
| Bandwidth | 717 GB/s | 1792 GB/s |
| Price (approx) | $1,549 | $12,999 |
| LLMs it runs | 27 of 48 | 41 of 48 |
| Best model it runs | Gemma 4 26B-A4B (MoE) · 141–212 tok/s | Gemma 4 31B · 20–30 tok/s |
The NVIDIA RTX Pro 6000 Blackwell (96GB) runs 14 more of the tracked models (41 vs 27), thanks to its 96.0 GB of memory. The NVIDIA RTX Pro 6000 Blackwell (96GB) has more memory bandwidth (1792 GB/s), so it generates tokens faster at the same model and quant.