A100 vs RTX 5090
Best sourced output tok/s per model (single-stream generation) — engine and version, quantization, context and a source link on every row. Hover a value for the quant.
A1000 sourced runs · best — tok/s
RTX 509023 verified runs · best 446.7 tok/s
Specs and evidence
| A100 | RTX 5090 | |
|---|---|---|
| VRAM | 40 GB | 32 GB |
| Sourced runs on the board | 0 | 23 |
| Models measured | 0 | 16 |
| Best output tok/s | — | 446.7 tok/s |
| Highest measured peak VRAM | — | 31.3 GB |
| Street price (latest snapshot) | — | — |
The measured matrix
| Model | A100 | RTX 5090 |
|---|---|---|
| NVIDIA-Nemotron-3.5-Lightning-30B-A3B | — | 446.7 |
| Qwen3.8-27B | — | 435.1 |
| Ornith-1.0-35B-PrismaAURA-4.75bit-vllm-MTP | — | 283.1 |
| Kimi-Linear-48B-A3B-Instruct | — | 280.8 |
| Ornith-1.5-35B-A3B | — | 258.8 |
| North-Mini-Code-1.0 | — | 258.4 |
| Qwen3.6-35B-A3B-MTP | — | 222.9 |
| Laguna-XS-2.1 | — | 216.7 |
| KAT-Coder-V2.5-Dev-AWQ-W4A16-ASYM | — | 201.2 |
| Ornith-1.0-35B | — | 196.6 |
| Muse-Glimmer-30B | — | 124.8 |
| Qwen3.6-27B | — | 120.9 |
| Huihui-Qwen3.8-27B-abliterated | — | 117.7 |
| Qwen3.8-27B-5090-goldilocks | — | 93.5 |
| Qwen3.6-27B-MTP | — | 28.3 |
| DeepSeek-V4-Flash-0731 | — | 26.4 |