Can an RTX 5090 run Qwen2.5-32B-Instruct?
llm-speed has not measured Qwen2.5-32B-Instruct on RTX 5090 itself yet, so there is no llm-speed verdict. 2 community-submitted runs exist (fastest 71.9 tok/s at an unreported quant on llama.cpp); community-submitted, not measured by llm-speed, so they give no verdict.
2 signed runs on llm-speed. Single-request decode speed in tokens per second; the short-chat workload unless noted. All 2 runs are 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 |
|---|---|---|---|---|---|---|
| not reported | llama.cpp | not reported | 71.9 | chat-short | 2 | 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.
VRAM: not recorded for these runs. The VRAM calculator gives an estimate (predicted, not measured).
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_twfs86tf_xf | 2026-07-01 | chat-short | – | llama.cpp · not reported | 0 | 256 | 71.9 | – | 115 | – | Community-submitted |
| r_bjy5a5izxjc | 2026-07-01 | chat-short | – | llama.cpp · not reported | 0 | 256 | 68.7 | – | 77 | – | Community-submitted |
| r_bjy5a5izxjc | 2026-07-01 | chat-long | – | llama.cpp · not reported | 0 | 326 | 65.4 | – | 968 | – | Community-submitted |
| r_bjy5a5izxjc | 2026-07-01 | agent-trace | – | llama.cpp · not reported | 3362 | 840 | 66.4 | 10407.9 | 214 | – | Community-submitted |
| r_bjy5a5izxjc | 2026-07-01 | concurrent-decode | – | llama.cpp · not reported | 1024 | 256 | 68.6 | – | – | – | Community-submitted |
Questions
Can an RTX 5090 run Qwen2.5-32B-Instruct?
llm-speed has not measured Qwen2.5-32B-Instruct on RTX 5090 itself yet, so there is no llm-speed verdict. 2 community-submitted runs exist (fastest 71.9 tok/s at an unreported quant on llama.cpp); community-submitted, not measured by llm-speed, so they give no verdict.
What did community runs measure for Qwen2.5-32B-Instruct on an RTX 5090?
2 community-submitted runs (community-submitted, not measured by llm-speed): not reported on llama.cpp: 71.9 tok/s. They are listed for reference and give no llm-speed verdict.