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
1Qwen2.5-7B-Instruct7BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
31,46 tok/s TG
Prefill 1.123 · TTFT 2.322 ms
1×Keine GPU (CPU-only)Apple M6 (unified CPU/GPU SoC, ARM64, AdvSIMD) · 24 GB RAMlmstudio-mlxlmstudioMLX 4bit
2Qwen2.5-7B-Instruct7BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
28,30 tok/s TG
Prefill 637 · TTFT 3.902 ms
1×Keine GPU (CPU-only)Apple M6 (unified CPU/GPU SoC) · 24 GB RAMOllamaopenclaw_cliQ4_K_M