r1 on RTX 4090 (24GB) + AMD EPYC 75F3 32-Core Processor (64c) + 504GB
RTX 4090 (24GB) + AMD EPYC 75F3 32-Core Processor (64c) + 504GB
suite suite-v1
cli 0.0.3
signedFisLG6Z90W…
Embed badgesubmitted Jul 02, 2026Workload results
| Workload | Backend | Model | decode tok/s | prefill tok/s | TTFT | p50 | p95 |
|---|---|---|---|---|---|---|---|
| chat-short | ollama@0.31.1 | deepseek-r1Q4_K_M | — | — | — | — | — |
| chat-long | ollama@0.31.1 | deepseek-r1Q4_K_M | 81.09tok/s | 240.4tok/s | 13,070ms | 12.3ms | 12.7ms |
| concurrent-decode | ollama@0.31.1 | deepseek-r1Q4_K_M | — | — | — | — | — |
| agent-trace | ollama@0.31.1 | deepseek-r1Q4_K_M | — | — | — | — | — |
Reproduce on your machine
Start with this model and workload selection. This command does not capture the original artifact, backend version or server settings:
Match quantization, context capacity, caching and runtime settings for a useful comparison. Duration varies by workload and hardware; the published client may differ from this run's version. How it's measured.
Embed this run
Drop the badge into a README, blog post, or signature. Each render is a backlink to the signed result.
[](https://llm-speed.com/r/r_zrjj-pj93q8)Related benchmarks
- More r1 benchmarks — every backend and rig that has run this model.
- More RTX 4090 (24GB) LLM benchmarks — every model measured on this hardware.
Provenance
- Run ID
- r_zrjj-pj93q8
- Fingerprint hash
- Public key
- FisLG6Z90WKISm7k1tccxqliAjeDcWuF8ItLJV69fuU=
- Received
- 2026-07-02 14:48:45