Can an RTX 5880 Ada run Llama 3.2 1B?
The answer
llm-speed has not measured Llama 3.2 1B on RTX 5880 Ada itself yet, so there is no llm-speed verdict. 1 community-submitted run exists (fastest 466.9 tok/s at Q8_0 on ollama); community-submitted, not measured by llm-speed, so it gives no verdict.
1 signed run on llm-speed. Single-request decode speed in tokens per second; the short-chat workload unless noted. This run is community-submitted (signed on the submitter's own machine, not measured by llm-speed, and not used for llm-speed verdicts). Verdicts and headline numbers use only llm-speed's own runs and fit tests.
Measured tok/s by quant and runtime
| Quant | Runtime | Build | Decode tok/s (best run) | Workload | Runs | Source |
|---|---|---|---|---|---|---|
| Q8_0 | ollama | 0.34.2 | 466.9 | chat-short | 1 | Community-submitted |
llm-speed has not measured this pair itself, so there is no llm-speed verdict or fastest quant. The rows above are community-submitted, not measured by llm-speed.
Check whether a model fits your GPU with the VRAM calculator.
Every measured row
| Run | Date (UTC) | Workload | Quant | Runtime / build | Prompt tokens | Output tokens | Decode tok/s | Prefill tok/s | TTFT ms | VRAM GiB | Source |
|---|---|---|---|---|---|---|---|---|---|---|---|
| r_b948ehgi8g4 | 2026-09-19 | chat-short | Q8_0 | ollama0.34.2 | 125 | 256 | 466.9 | 44.3 | 2821 | – | Community-submitted |
| r_b948ehgi8g4 | 2026-09-19 | chat-long | Q8_0 | ollama0.34.2 | 3152 | 273 | 441.9 | 39673.0 | 79 | – | Community-submitted |
| r_b948ehgi8g4 | 2026-09-19 | agent-trace | Q8_0 | ollama0.34.2 | 3225 | 840 | 452.3 | 91077.2 | 22 | – | Community-submitted |
| r_b948ehgi8g4 | 2026-09-19 | concurrent-decode | Q8_0 | ollama0.34.2 | 1024 | 256 | 464.2 | – | – | – | Community-submitted |
Questions
Can an RTX 5880 Ada run Llama 3.2 1B?
llm-speed has not measured Llama 3.2 1B on RTX 5880 Ada itself yet, so there is no llm-speed verdict. 1 community-submitted run exists (fastest 466.9 tok/s at Q8_0 on ollama); community-submitted, not measured by llm-speed, so it gives no verdict.
What did community runs measure for Llama 3.2 1B on an RTX 5880 Ada?
1 community-submitted run (community-submitted, not measured by llm-speed): Q8_0 on ollama: 466.9 tok/s. They are listed for reference and give no llm-speed verdict.