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:
GPUs
#Model / MakerMetricsParallelGPU / CPU / RAMRuntime
1Llama-3.2-1B-Instruct1BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
133,16 tok/s TG
Prefill 7.177 · TTFT 377 ms
1×Keine GPU (CPU-only)Apple M6 (unified CPU/GPU SoC, ARM64, AdvSIMD) · 24 GB RAMlmstudio-mlxlmstudioMLX 4bit
2Llama-3.2-1B-Instruct1BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
97,11 tok/s TG
Prefill 5.083 · TTFT 500 ms
1×Keine GPU (CPU-only)Apple M6 (unified CPU/GPU SoC) · 24 GB RAMOllamaopenclaw_cliQ8_0
3Llama-3.2-1B-Instruct1BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
13,17 tok/s TG
Prefill 122 · TTFT 228.054 ms
10×Keine GPU (CPU-only) i4 x Cortex-A78C + 4 x Cortex-A55 · 15 GB RAMllama.cppopenclaw_cliQ4_K_M
4Llama-3.2-1B-Instruct1BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
12,93 tok/s TG
Prefill 95 · TTFT 136.105 ms
5×Keine GPU (CPU-only) i4 x Cortex-A78C + 4 x Cortex-A55 · 15 GB RAMllama.cppopenclaw_cliQ4_K_M
5Llama-3.2-1B-Instruct1BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
7,33 tok/s TG
Prefill 65 · TTFT 38.290 ms
1×Keine GPU (CPU-only) i4 x Cortex-A78C + 4 x Cortex-A55 · 15 GB RAMllama.cppopenclaw_cliQ4_K_M
6Llama-3.2-1B-Instruct1BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
609,48 tok/s TG
Prefill 31.648 · TTFT 962 ms
10×2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_M
7Llama-3.2-1B-Instruct1BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
376,49 tok/s TG
Prefill 22.247 · TTFT 615 ms
5×2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_M
8Llama-3.2-1B-Instruct1BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
207,12 tok/s TG
Prefill 7.688 · TTFT 400 ms
1×2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_M
9Llama-3.2-1B-Instruct1BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
717,61 tok/s TG
Prefill 52.503 · TTFT 1.022 ms
10×2x AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAMvLLMgodclaw
10Llama-3.2-1B-Instruct1BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
479,20 tok/s TG
Prefill 40.760 · TTFT 356 ms
5×2x AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAMvLLMgodclaw
11Llama-3.2-1B-Instruct1BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
98,26 tok/s TG
Prefill 15.904 · TTFT 156 ms
1×2x AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAMvLLMgodclaw
12Llama-3.2-1B-Instruct1BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
696,81 tok/s TG
Prefill 41.362 · TTFT 722 ms
10×2x AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAMllama.cppgodclawQ4_K_M
13Llama-3.2-1B-Instruct1BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
443,74 tok/s TG
Prefill 31.085 · TTFT 445 ms
5×2x AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAMllama.cppgodclawQ4_K_M
14Llama-3.2-1B-Instruct1BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
209,03 tok/s TG
Prefill 11.184 · TTFT 257 ms
1×2x AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAMllama.cppgodclawQ4_K_M
15Llama-3.2-1B-Instruct1BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
43,17 tok/s TG
Prefill 281 · TTFT 8.805 ms
1×AMD Liverpool (PlayStation 4)AMD Jaguar 8-Core (PlayStation 4) · 5 GB RAMllama.cppgodclawQ4_K_M
16Llama-3.2-1B-Instruct1BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
3,91 tok/s TG
Prefill 193 · TTFT 12.786 ms
1×Keine GPU (CPU-only)AMD Jaguar 8-Core (PlayStation 4) · 5 GB RAMllama.cppgodclawQ4_K_M