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
1Muse-Glimmer-30B29.8Bmeta-models Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
171,83 tok/s TG
Prefill 1.188 · TTFT 16.950 ms
10×AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAMllama.cppopenclaw_cliQ4_K_M
2Muse-Glimmer-30B29.8Bmeta-models Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
72,58 tok/s TG
Prefill 1.050 · TTFT 9.383 ms
5×AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAMllama.cppopenclaw_cliQ4_K_M
3Muse-Glimmer-30B29.8Bmeta-models Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
27,32 tok/s TG
Prefill 999 · TTFT 1.966 ms
1×AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAMllama.cppopenclaw_cliQ4_K_M