Created bymario-alka.dePowered bynoob2claw.detricoma.de
🏆
Rankings

LLM Leaderboard

Real measurements of every tested language model on real, named hardware – rated by raw speed (performance in tokens per second, prefill and time to first token) and by practical task quality in complete agent and chat runs (harness). Pick a benchmark type below or filter by model, maker and hardware to see exactly what is tested and how the results are produced.

⚡ Performance (tok/s)🤖 Harness quality👥 Concurrency🖥️ real hardware
Reset
Metric:
#Model / MakerMetricsParallelGPU / CPU / RAMRuntime
1Qwen3.6-27B27BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
532,52 tok/s TG
Prefill 3.040 · TTFT 21.374 ms
10×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliQ4_K_M
2Qwen3.6-27B27BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
282,12 tok/s TG
Prefill 2.726 · TTFT 7.017 ms
5×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliQ4_K_M
3Qwen3.6-27B27BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
74,70 tok/s TG
Prefill 1.851 · TTFT 1.045 ms
1×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliQ4_K_M