Created bymario-alka.dePowered bygodcore.denoob2claw.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
1MiniMax-M2.5230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
551,03 tok/s TG
Prefill 5.883 · TTFT 19.730 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_M
2MiniMax-M2.5230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
549,26 tok/s TG
Prefill 5.889 · TTFT 19.774 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_M
3MiniMax-M2.7230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
548,62 tok/s TG
Prefill 4.931 · TTFT 20.370 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawUD-Q4_K_M
4MiniMax-M2.5230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
548,49 tok/s TG
Prefill 6.245 · TTFT 19.796 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_M
5MiniMax-M2.5230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
548,08 tok/s TG
Prefill 6.142 · TTFT 19.770 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_M
6minimax-m2-awq230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
547,88 tok/s TG
Prefill 4.819 · TTFT 20.318 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawUD-Q4_K_M
7MiniMax-M2.5230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
545,64 tok/s TG
Prefill 4.494 · TTFT 20.927 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_M
8MiniMax-M2.5230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
530,92 tok/s TG
Prefill 4.560 · TTFT 20.923 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_M
9MiniMax-M2.7230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
530,51 tok/s TG
Prefill 4.240 · TTFT 21.543 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawUD-Q4_K_M
10MiniMax-M2.5230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
316,86 tok/s TG
Prefill 5.641 · TTFT 6.113 ms
5×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_M
11MiniMax-M2.5230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
315,17 tok/s TG
Prefill 5.986 · TTFT 6.075 ms
5×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_M
12MiniMax-M2.5230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
314,98 tok/s TG
Prefill 5.475 · TTFT 6.192 ms
5×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_M
13MiniMax-M2.5230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
313,12 tok/s TG
Prefill 5.523 · TTFT 6.054 ms
5×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_M
14MiniMax-M2.5230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
312,76 tok/s TG
Prefill 4.300 · TTFT 6.842 ms
5×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_M
15MiniMax-M2.7230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
312,31 tok/s TG
Prefill 4.491 · TTFT 6.623 ms
5×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawUD-Q4_K_M
16MiniMax-M2.5230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
310,92 tok/s TG
Prefill 4.407 · TTFT 6.814 ms
5×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_M
17minimax-m2-awq230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
310,36 tok/s TG
Prefill 4.459 · TTFT 6.645 ms
5×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawUD-Q4_K_M
18MiniMax-M2.7230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
305,98 tok/s TG
Prefill 3.962 · TTFT 7.171 ms
5×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawUD-Q4_K_M
19MiniMax-M2.7230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
174,20 tok/s TG
Prefill 5.042 · TTFT 47.620 ms
10×NVIDIA GB10 (DGX Spark)NVIDIA Grace · 120 GB RAMvLLMgodclawAWQ
20MiniMax-M2.5230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
116,21 tok/s TG
Prefill 2.989 · TTFT 767 ms
1×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_M
21MiniMax-M2.5230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
116,18 tok/s TG
Prefill 2.914 · TTFT 786 ms
1×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_M
22MiniMax-M2.5230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
116,16 tok/s TG
Prefill 2.988 · TTFT 766 ms
1×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_M
23MiniMax-M2.5230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
115,73 tok/s TG
Prefill 2.954 · TTFT 777 ms
1×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_M
24MiniMax-M2.7230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
112,80 tok/s TG
Prefill 1.953 · TTFT 1.180 ms
1×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawUD-Q4_K_M
25minimax-m2-awq230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
112,64 tok/s TG
Prefill 2.405 · TTFT 972 ms
1×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawUD-Q4_K_M
26MiniMax-M2.7230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
112,58 tok/s TG
Prefill 2.290 · TTFT 1.014 ms
1×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawUD-Q4_K_M
27MiniMax-M2.5230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
108,97 tok/s TG
Prefill 2.358 · TTFT 971 ms
1×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_M
28MiniMax-M2.7230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
108,63 tok/s TG
Prefill 4.568 · TTFT 13.673 ms
5×NVIDIA GB10 (DGX Spark)NVIDIA Grace · 120 GB RAMvLLMgodclawAWQ
29MiniMax-M2.5230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
106,92 tok/s TG
Prefill 2.238 · TTFT 1.025 ms
1×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_M
30MiniMax-M2.7230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
106,12 tok/s TG
Prefill 5.634 · TTFT 12.854 ms
5×NVIDIA GB10 (DGX Spark)NVIDIA Grace · 120 GB RAMvLLMgodclawAWQ
31MiniMax-M2.5230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
105,57 tok/s TG
Prefill 6.997 · TTFT 5.319 ms
10×NVIDIA GB10 (DGX Spark)NVIDIA Grace · 120 GB RAMvLLMgodclawAWQ
32MiniMax-M2.5230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
103,49 tok/s TG
Prefill 7.016 · TTFT 5.294 ms
10×NVIDIA GB10 (DGX Spark)NVIDIA Grace · 120 GB RAMvLLMgodclawAWQ
33MiniMax-M2.7230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
103,25 tok/s TG
Prefill 6.620 · TTFT 5.066 ms
10×NVIDIA GB10 (DGX Spark)NVIDIA Grace · 120 GB RAMvLLMgodclawAWQ
34MiniMax-M2.5230BMiniMax Harness benchmarkTool Usage Standard 1.0
2.427 Pkt
81,4% · 16/16 Aufg. · 228,0 s
1×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMvLLMgodclawBF16
35MiniMax-M2.5230BMiniMax Harness benchmarkTool Usage Standard 1.0
2.340 Pkt
78,5% · 16/16 Aufg. · 266,0 s
1×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMopenclaw_cli
36MiniMax-M2.5230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
77,74 tok/s TG
Prefill 5.460 · TTFT 2.641 ms
5×NVIDIA GB10 (DGX Spark)NVIDIA Grace · 120 GB RAMvLLMgodclawAWQ
37MiniMax-M2.5230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
73,44 tok/s TG
Prefill 5.550 · TTFT 2.628 ms
5×NVIDIA GB10 (DGX Spark)NVIDIA Grace · 120 GB RAMvLLMgodclawAWQ
38MiniMax-M2.5230BMiniMax Harness benchmarkTool Usage V 1.0
1.245 Pkt
70,7% · 15/15 Aufg. · 301,0 s
1×NVIDIA GB10 (DGX Spark)NVIDIA Grace · 120 GB RAMopenclaw_cli
39MiniMax-M2.5230BMiniMax Harness benchmarkTool Usage Standard 1.0
2.033 Pkt
68,2% · 16/16 Aufg. · 373,0 s
1×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMvLLMgodclawBF16
40MiniMax-M2.7230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
66,75 tok/s TG
Prefill 6.946 · TTFT 4.901 ms
10×NVIDIA GB10 (DGX Spark)NVIDIA Grace · 120 GB RAMvLLMgodclawAWQ
41MiniMax-M2.5230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
66,09 tok/s TG
Prefill 469 · TTFT 10.919 ms
10×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cli batched-bench ROCmQ4_K_M
42MiniMax-M2.5230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
66,09 tok/s TG
Prefill 469 · TTFT 0 ms
10×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cli batched-bench
43MiniMax-M2.5230BMiniMax Harness benchmarkTools Usage Mini 1.0
130 Pkt
65,0% · 2/2 Aufg. · 70,0 s
1×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMgodclaw
44MiniMax-M2.7230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
64,45 tok/s TG
Prefill 7.167 · TTFT 4.743 ms
10×NVIDIA GB10 (DGX Spark)NVIDIA Grace · 120 GB RAMvLLMgodclawAWQ
45MiniMax-M2.5230BMiniMax Performance benchmarkPerformancetest Small 1.0
62,70 tok/s TG
Prefill 368 · TTFT 144 ms
1×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMvLLMgodclawBF16
46MiniMax-M2.5230BMiniMax Performance benchmark
62,70 tok/s TG
Prefill 368 · TTFT 144 ms
1×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition34x AMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMgodclawBF16
47MiniMax-M2.5230BMiniMax Harness benchmarkTool Usage V 1.0
1.079 Pkt
61,3% · 15/15 Aufg. · 457,0 s
1×2x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMopenclaw_cli
48MiniMax-M2.7230BMiniMax Harness benchmarkTool-Parcours Dossier 40 V1.0
3.641 Pkt
61,1% · 40/40 Aufg. · 8.209,0 s
1×NVIDIA GB10 (DGX Spark)NVIDIA Grace · 120 GB RAMvLLMgodclawAWQ
49MiniMax-M2.5230BMiniMax Harness benchmarkTool-Parcours Dossier 40 V1.0
3.622 Pkt
60,8% · 34/40 Aufg. · 7.862,0 s
1×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMvLLMgodclawBF16
50MiniMax-M2.5230BMiniMax Harness benchmarkTool Usage Standard 1.0
1.762 Pkt
59,1% · 16/16 Aufg. · 526,0 s
1×NVIDIA GB10 (DGX Spark)NVIDIA Grace · 120 GB RAMopenclaw_cli
51MiniMax-M2.5230BMiniMax Harness benchmarkTool Usage Standard 1.0
1.714 Pkt
57,5% · 16/16 Aufg. · 487,0 s
1×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMvLLMgodclawBF16
52MiniMax-M2.5230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
56,11 tok/s TG
Prefill 442 · TTFT 5.792 ms
5×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cli batched-bench ROCmQ4_K_M
53MiniMax-M2.5230BMiniMax Harness benchmarkTools Usage Mini 1.0
106 Pkt
53,0% · 2/2 Aufg. · 71,0 s
1×2x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMopenclaw_cli
54MiniMax-M2.7230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
52,46 tok/s TG
Prefill 5.268 · TTFT 2.720 ms
5×NVIDIA GB10 (DGX Spark)NVIDIA Grace · 120 GB RAMvLLMgodclawAWQ
55MiniMax-M2.5230BMiniMax Harness benchmarkTextgenerierung V 1.0
790 Pkt
52,0% · 15/15 Aufg. · 261,0 s
1×NVIDIA GB10 (DGX Spark)NVIDIA Grace · 120 GB RAMopenclaw_cli
56MiniMax-M2.7230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
51,61 tok/s TG
Prefill 5.448 · TTFT 2.676 ms
5×NVIDIA GB10 (DGX Spark)NVIDIA Grace · 120 GB RAMvLLMgodclawAWQ
57MiniMax-M2.7230BMiniMax Performance benchmarkPerformancetest Small 1.0
34,37 tok/s TG
Prefill 503 · TTFT 105 ms
1×NVIDIA GB10 (DGX Spark)NVIDIA Grace · 120 GB RAMvLLMgodclawAWQ
58MiniMax-M2.5230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
32,23 tok/s TG
Prefill 2.184 · TTFT 1.050 ms
1×NVIDIA GB10 (DGX Spark)NVIDIA Grace · 120 GB RAMvLLMgodclawAWQ
59MiniMax-M2.5230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
31,93 tok/s TG
Prefill 2.096 · TTFT 1.093 ms
1×NVIDIA GB10 (DGX Spark)NVIDIA Grace · 120 GB RAMvLLMgodclawAWQ
60MiniMax-M2.7230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
31,52 tok/s TG
Prefill 2.328 · TTFT 991 ms
1×NVIDIA GB10 (DGX Spark)NVIDIA Grace · 120 GB RAMvLLMgodclawAWQ
61MiniMax-M2.7230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
29,35 tok/s TG
Prefill 1.986 · TTFT 1.157 ms
1×NVIDIA GB10 (DGX Spark)NVIDIA Grace · 120 GB RAMvLLMgodclawAWQ
62MiniMax-M2.7230BMiniMax Harness benchmarkTool Usage Standard 1.0
858 Pkt
28,8% · 16/16 Aufg. · 1.222,0 s
1×NVIDIA GB10 (DGX Spark)NVIDIA Grace · 120 GB RAMgodclaw
63MiniMax-M2.5230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
28,40 tok/s TG
Prefill 248 · TTFT 2.063 ms
1×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cli batched-bench ROCmQ4_K_M
64MiniMax-M2.7230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
24,25 tok/s TG
Prefill 2.437 · TTFT 960 ms
1×NVIDIA GB10 (DGX Spark)NVIDIA Grace · 120 GB RAMvLLMgodclawAWQ
65MiniMax-M2.7230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
24,01 tok/s TG
Prefill 2.068 · TTFT 1.108 ms
1×NVIDIA GB10 (DGX Spark)NVIDIA Grace · 120 GB RAMvLLMgodclawAWQ
66MiniMax-M2.5230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
22,54 tok/s TG
Prefill 135 · TTFT 163.713 ms
5×NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMllama.cppgodclawQ4_K_M
67MiniMax-M2.5230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
21,85 tok/s TG
Prefill 141 · TTFT 157.949 ms
5×NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMllama.cppgodclawQ4_K_M
68MiniMax-M2.5230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
21,24 tok/s TG
Prefill 124 · TTFT 182.622 ms
5×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
69MiniMax-M2.5230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
19,28 tok/s TG
Prefill 178 · TTFT 83.659 ms
5×AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMllama.cppgodclawQ4_K_M
70MiniMax-M2.5230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
19,07 tok/s TG
Prefill 122 · TTFT 175.708 ms
5×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
71MiniMax-M2.5230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
19,04 tok/s TG
Prefill 173 · TTFT 85.620 ms
5×2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMllama.cppgodclawQ4_K_M
72MiniMax-M2.5230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
18,16 tok/s TG
Prefill 202 · TTFT 159.916 ms
10×2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMllama.cppgodclawQ4_K_M
73MiniMax-M2.5230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
18,13 tok/s TG
Prefill 206 · TTFT 156.546 ms
10×AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMllama.cppgodclawQ4_K_M
74minimax-m2-awq230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
16,95 tok/s TG
Prefill 113 · TTFT 190.982 ms
5×NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMllama.cppgodclawUD-Q4_K_M
75MiniMax-M2.5230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
15,90 tok/s TG
Prefill 157 · TTFT 163.779 ms
5×NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAMllama.cppwebsocketQ4_K_M
76MiniMax-M2.5230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
15,80 tok/s TG
Prefill 156 · TTFT 171.016 ms
5×NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAMllama.cppwebsocketQ4_K_M
77MiniMax-M2.5230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
15,20 tok/s TG
Prefill 123 · TTFT 182.689 ms
5×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
78MiniMax-M2.5230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
15,16 tok/s TG
Prefill 152 · TTFT 287.291 ms
10×NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMllama.cppgodclawQ4_K_M
79MiniMax-M2.5230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
14,58 tok/s TG
Prefill 92 · TTFT 24.881 ms
1×2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMllama.cppgodclawQ4_K_M
80MiniMax-M2.7230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
14,51 tok/s TG
Prefill 104 · TTFT 153.543 ms
5×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawUD-Q4_K_M
81MiniMax-M2.5230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
14,50 tok/s TG
Prefill 93 · TTFT 24.739 ms
1×AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMllama.cppgodclawQ4_K_M
82minimax-m2-awq230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
13,28 tok/s TG
Prefill 120 · TTFT 263.391 ms
10×NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMllama.cppgodclawUD-Q4_K_M
83MiniMax-M2.5230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
13,22 tok/s TG
Prefill 153 · TTFT 277.094 ms
10×NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMllama.cppgodclawQ4_K_M
84MiniMax-M2.7230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
12,89 tok/s TG
Prefill 103 · TTFT 154.280 ms
5×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawUD-Q4_K_M
85MiniMax-M2.5230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
12,68 tok/s TG
Prefill 128 · TTFT 259.946 ms
10×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
86MiniMax-M2.5230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
12,63 tok/s TG
Prefill 153 · TTFT 195.676 ms
10×NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAMllama.cppwebsocketQ4_K_M
87MiniMax-M2.7230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
12,34 tok/s TG
Prefill 103 · TTFT 154.375 ms
5×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawUD-Q4_K_M
88MiniMax-M2.5230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
11,86 tok/s TG
Prefill 87 · TTFT 26.343 ms
1×NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMllama.cppgodclawQ4_K_M
89MiniMax-M2.5230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
11,45 tok/s TG
Prefill 84 · TTFT 27.256 ms
1×NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMllama.cppgodclawQ4_K_M
90MiniMax-M2.5230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
11,25 tok/s TG
Prefill 148 · TTFT 197.892 ms
10×NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAMllama.cppwebsocketQ4_K_M
91MiniMax-M2.5230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
10,98 tok/s TG
Prefill 126 · TTFT 212.275 ms
10×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
92MiniMax-M2.5230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
10,76 tok/s TG
Prefill 124 · TTFT 212.594 ms
10×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
93minimax-m2-awq230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
10,53 tok/s TG
Prefill 67 · TTFT 34.091 ms
1×NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMllama.cppgodclawUD-Q4_K_M
94MiniMax-M2.5230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
10,51 tok/s TG
Prefill 65 · TTFT 35.289 ms
1×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
95MiniMax-M2.5230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
10,35 tok/s TG
Prefill 65 · TTFT 35.241 ms
1×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
96MiniMax-M2.5230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
10,34 tok/s TG
Prefill 66 · TTFT 34.976 ms
1×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
97MiniMax-M2.5230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
10,22 tok/s TG
Prefill 107 · TTFT 138.875 ms
5×2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMllama.cppgodclawQ8_0
98MiniMax-M2.5230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
10,05 tok/s TG
Prefill 57 · TTFT 40.222 ms
1×2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMllama.cppgodclawQ8_0
99MiniMax-M2.5230BMiniMax Harness benchmarkTools Usage Mini 1.0
10 Pkt
10,0% · 1/1 Aufg. · 65,0 s
1×2x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMopenclaw_cli
100MiniMax-M2.5230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
9,95 tok/s TG
Prefill 57 · TTFT 40.441 ms
1×AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMllama.cppgodclawQ8_0
101MiniMax-M2.5230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
9,89 tok/s TG
Prefill 102 · TTFT 140.902 ms
5×AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMllama.cppgodclawQ8_0
102MiniMax-M2.7230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
9,03 tok/s TG
Prefill 49 · TTFT 47.605 ms
1×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawUD-Q4_K_M
103MiniMax-M2.7230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
8,97 tok/s TG
Prefill 41 · TTFT 59.968 ms
1×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawUD-Q4_K_M
104MiniMax-M2.7230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
8,96 tok/s TG
Prefill 41 · TTFT 60.147 ms
1×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawUD-Q4_K_M
105minimax-m2-awq230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
8,67 tok/s TG
Prefill 86 · TTFT 121.821 ms
5×NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAMllama.cppgodclawUD-Q4_K_M
106MiniMax-M2.7230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
8,62 tok/s TG
Prefill 104 · TTFT 186.906 ms
10×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawUD-Q4_K_M
107MiniMax-M2.5230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
8,54 tok/s TG
Prefill 111 · TTFT 273.337 ms
10×AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMllama.cppgodclawQ8_0
108MiniMax-M2.7230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
8,38 tok/s TG
Prefill 105 · TTFT 186.362 ms
10×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawUD-Q4_K_M
109MiniMax-M2.5230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
8,22 tok/s TG
Prefill 70 · TTFT 38.073 ms
1×NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAMllama.cppwebsocketQ4_K_M
110MiniMax-M2.5230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
8,20 tok/s TG
Prefill 72 · TTFT 35.231 ms
1×NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAMllama.cppwebsocketQ4_K_M
111MiniMax-M2.5230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
8,01 tok/s TG
Prefill 109 · TTFT 274.848 ms
10×2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMllama.cppgodclawQ8_0
112minimax-m2-awq230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
7,51 tok/s TG
Prefill 98 · TTFT 111.122 ms
10×NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAMllama.cppgodclawUD-Q4_K_M
113MiniMax-M2.7230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
7,29 tok/s TG
Prefill 105 · TTFT 186.321 ms
10×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawUD-Q4_K_M
114MiniMax-M2.7230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
7,06 tok/s TG
Prefill 266 · TTFT 8.622 ms
1×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
115MiniMax-M2.5230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
7,03 tok/s TG
Prefill 253 · TTFT 9.057 ms
1×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
116MiniMax-M2.5230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
7,01 tok/s TG
Prefill 250 · TTFT 9.170 ms
1×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
117MiniMax-M2.7230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
7,00 tok/s TG
Prefill 96 · TTFT 109.168 ms
10×NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAMllama.cppgodclawUD-Q4_K_M
118MiniMax-M2.5230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
7,00 tok/s TG
Prefill 120 · TTFT 140.976 ms
5×NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAMllama.cppgodclawQ4_K_M
119MiniMax-M2.5230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
6,46 tok/s TG
Prefill 119 · TTFT 21.346 ms
1×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawIQ4_NL
120MiniMax-M2.5230BMiniMax Performance benchmark
6,46 tok/s TG
Prefill 119 · TTFT 21.346 ms
1×3x AMD Radeon AI PRO R970032x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMgodclaw
121MiniMax-M2.7230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
6,30 tok/s TG
Prefill 94 · TTFT 111.517 ms
5×NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAMllama.cppgodclawUD-Q4_K_M
122MiniMax-M2.5230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
6,02 tok/s TG
Prefill 65 · TTFT 35.247 ms
1×NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAMllama.cppgodclawQ4_K_M
123MiniMax-M2.7230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
5,96 tok/s TG
Prefill 73 · TTFT 143.452 ms
10×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliUD-Q4_K_M
124MiniMax-M2.7230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
5,95 tok/s TG
Prefill 67 · TTFT 150.288 ms
5×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliUD-Q4_K_M
125MiniMax-M2.7230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
5,85 tok/s TG
Prefill 71 · TTFT 147.489 ms
5×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliUD-Q4_K_M
126MiniMax-M2.7230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
5,22 tok/s TG
Prefill 53 · TTFT 44.470 ms
1×NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAMllama.cppgodclawUD-Q4_K_M
127minimax-m2-awq230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
5,22 tok/s TG
Prefill 55 · TTFT 42.011 ms
1×NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAMllama.cppgodclawUD-Q4_K_M
128MiniMax-M2.7230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
4,79 tok/s TG
Prefill 75 · TTFT 140.576 ms
10×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliUD-Q4_K_M
129MiniMax-M2.7230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
4,78 tok/s TG
Prefill 95 · TTFT 110.730 ms
10×NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAMllama.cppgodclawUD-Q4_K_M
130MiniMax-M2.7230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
4,61 tok/s TG
Prefill 717 · TTFT 35.394 ms
10×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
131MiniMax-M2.5230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
4,37 tok/s TG
Prefill 62 · TTFT 36.988 ms
1×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliQ4_K_M
132MiniMax-M2.5230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
4,32 tok/s TG
Prefill 61 · TTFT 37.512 ms
1×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliQ4_K_M
133MiniMax-M2.5230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
4,31 tok/s TG
Prefill 119 · TTFT 88.713 ms
10×NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAMllama.cppgodclawQ4_K_M
134MiniMax-M2.5230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
4,12 tok/s TG
Prefill 50 · TTFT 45.694 ms
1×NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAMllama.cppgodclawQ4_K_M
135MiniMax-M2.7230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
3,95 tok/s TG
Prefill 10 · TTFT 246.180 ms
1×NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAMllama.cppwebsocketUD-Q4_K_M
136MiniMax-M2.5230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
3,93 tok/s TG
Prefill 94 · TTFT 112.413 ms
10×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliQ4_K_M
137MiniMax-M2.7230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
3,92 tok/s TG
Prefill 600 · TTFT 23.512 ms
5×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
138MiniMax-M2.5230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
3,91 tok/s TG
Prefill 71 · TTFT 147.578 ms
5×NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAMllama.cppgodclawQ4_K_M
139MiniMax-M2.7230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
3,42 tok/s TG
Prefill 83 · TTFT 117.412 ms
5×NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAMllama.cppgodclawUD-Q4_K_M
140MiniMax-M2.5230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
3,39 tok/s TG
Prefill 391 · TTFT 32.665 ms
5×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
141MiniMax-M2.7230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
3,34 tok/s TG
Prefill 44 · TTFT 52.253 ms
1×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliUD-Q4_K_M
142MiniMax-M2.5230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
3,23 tok/s TG
Prefill 434 · TTFT 75.130 ms
5×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
143MiniMax-M2.5230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
3,16 tok/s TG
Prefill 89 · TTFT 115.055 ms
5×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliQ4_K_M
144MiniMax-M2.5230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
3,01 tok/s TG
Prefill 89 · TTFT 114.283 ms
10×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliQ4_K_M
145MiniMax-M2.7230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
3,00 tok/s TG
Prefill 139 · TTFT 15.493 ms
1×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawUD-Q4_K_M
146MiniMax-M2.7230BMiniMax Performance benchmark
3,00 tok/s TG
Prefill 139 · TTFT 15.493 ms
1×3x AMD Radeon AI PRO R970032x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMgodclawQ4_K_M
147MiniMax-M2.5230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
2,92 tok/s TG
Prefill 510 · TTFT 38.845 ms
10×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
148MiniMax-M2.5230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
2,72 tok/s TG
Prefill 92 · TTFT 114.221 ms
5×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliQ4_K_M
149MiniMax-M2.7230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
2,62 tok/s TG
Prefill 15 · TTFT 156.050 ms
1×2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAMllama.cppgodclawUD-Q4_K_M
150MiniMax-M2.5230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
1,86 tok/s TG
Prefill 73 · TTFT 138.925 ms
10×NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAMllama.cppgodclawQ4_K_M
151MiniMax-M2.5230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
0,84 tok/s TG
Prefill 22 · TTFT 98.716 ms
1×2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAMllama.cppgodclawQ4_K_M
152MiniMax-M2.7230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
0,04 tok/s TG
Prefill 29 · TTFT 211.132 ms
5×2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAMllama.cppgodclawUD-Q4_K_M
153MiniMax-M2.7230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
0,03 tok/s TG
Prefill 28 · TTFT 212.753 ms
10×2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAMllama.cppgodclawUD-Q4_K_M
154MiniMax-M2.7230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
0,01 tok/s TG
Prefill 11 · TTFT 381.533 ms
10×NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAMllama.cppwebsocketUD-Q4_K_M
155MiniMax-M2.7230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
0,01 tok/s TG
Prefill 10 · TTFT 410.716 ms
5×NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAMllama.cppwebsocketUD-Q4_K_M