Qwen3.8-27B-5090-goldilocks
Qwen family · 28.0B params
1recorded run
93.5best tok/s
1verified
Fastest GPUs for this model (best tok/s)
- RTX 509093.5
All benchmarks Methodology
| GPU | Model | Quant | Backend | Ctx |
tok/s | prompt tok/s | VRAM GB | Source |
| RTX 5090 · 32 GB | Qwen3.8-27B-5090-goldilocks | Q6_K | llama.cpp 10437, commit 16d222fc5 | 131000 | 93.5 ✓ | 2038.8 | 29.8 | src |