RTX 5880 Ada LLM benchmark
The highest recorded decode rate in these RTX 5880 Ada submissions is from llama3.2 (1.2B) at 466.9 decode tok/s via ollama (source run). This page contains 4 workload rows from 1 submitted run across 1 model. Model sizes, workloads and reported hardware configurations differ; the highest rate is not a quality ranking or a speed guarantee.
Specs vendor specs, not measured
- VRAM
- 48 GB
- Memory bandwidth
- 960 GB/s
Sources: nvidia.com, nvidia.cn. Vendor-published figures, accessed 2026-10-14.
Fastest single result in these submissions (any model size)
466.9 decode tok/s
llama3.2 (1.2B) via ollama (Q8_0). Workload: chat-short. Reported hardware: RTX 5880 (48GB). see full run
llama3.2
| Workload | Model size | Reported hardware | Backend | Quant | decode tok/s | prefill tok/s | TTFT | Run | Source |
|---|---|---|---|---|---|---|---|---|---|
| chat-short | 1.2B | RTX 5880 (48GB) | ollama0.34.2 | Q8_0 | 466.9tok/s | 44.32tok/s | 2,821ms | r_b948ehgi8g4 | Community-submitted |
| chat-long | 1.2B | RTX 5880 (48GB) | ollama0.34.2 | Q8_0 | 441.9tok/s | 39,673.0tok/s | 79.4ms | r_b948ehgi8g4 | Community-submitted |
| concurrent-decode | 1.2B | RTX 5880 (48GB) | ollama0.34.2 | Q8_0 | 464.2tok/s | no data | no data | r_b948ehgi8g4 | Community-submitted |
| agent-trace | 1.2B | RTX 5880 (48GB) | ollama0.34.2 | Q8_0 | 452.3tok/s | 91,077.2tok/s | 21.8ms | r_b948ehgi8g4 | Community-submitted |
Which models can an RTX 5880 Ada run?
Fastest decode speed for each model on this hardware, from llm-speed's own runs and community-submitted runs. Each page lists every quant and runtime and labels which runs llm-speed measured.
Models measured on RTX 5880 Ada
Request a run on RTX 5880 Ada
No measured run yet for these pairs. Vote for the one you want; the most-requested runs go first. See all requests.
We never sell or share your email. Privacy