RTX 4090
Nvidia · 24 GB VRAM
2recorded runs
141.2best tok/s
2sourced
How it compares — 24 GB tier
Best verified tok/s per GPU in this VRAM tier — compare any two like-for-like.
Evidence: 2 sourced runs · 2 independent sources · first recorded Aug 19, 2026 · last recorded Sep 15, 2026. What these labels mean.
All benchmarks Compare RTX 4090 →
| GPU | Model | Quant | Backend | Ctx |
tok/s | prompt tok/s | VRAM GB | Source |
| RTX 4090 · 24 GB | Qwen3.8-27B | int4 (output head only) | vllm pinned version (exact version not sp… | 38000 | 141.2 ✓ | — | — | src |
| RTX 4090 · 24 GB | Qwen3.8-27B | UD-Q4_K_XL | llama.cpp llama.cpp 7e4c0a96880dae4fc4268ad441… | 172032 | 91.6 ✓ | 968.5 | — | src |
Related reading: GPU buying guide · used GPUs · Value index · Street prices