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
1Qwen2.5-32B-Instruct-AWQ32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
222,01 tok/s TG
Prefill 2.436 · TTFT 45.755 ms
10×NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAMllama.cppwebsocketAWQ
2Qwen2.5-32B-Instruct-AWQ32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
124,33 tok/s TG
Prefill 2.267 · TTFT 13.440 ms
5×NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAMllama.cppwebsocketAWQ
3Qwen2.5-32B-Instruct-AWQ32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
40,18 tok/s TG
Prefill 1.444 · TTFT 1.705 ms
1×NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAMllama.cppwebsocketAWQ