🧮
Mainboard
Micro-Star International Co., Ltd. B550M PRO-VDH WIFI (MS-7C95)
Other1 CPU11 Benchmarks
CPUs
1
Models
3
Benchmarks
11
Best generation
400,4 tok/s
🏆
Qwen3-Coder-30B-A3B-Instruct läuft am schnellsten auf diesem Board · 400,4 tok/s
3 Modelle mit Performance-Daten getestet
3 Modelle mit Performance-Daten getestet
Top models by token generation
Bester gemessener Generierungs-Durchsatz je Modell auf Micro-Star International Co., Ltd. B550M PRO-VDH WIFI (MS-7C95) (tok/s) – klicken für Leaderboard-Filter.
Anzeige
Model comparison
Tested models compared
Jede Blase ist ein Modell auf Micro-Star International Co., Ltd. B550M PRO-VDH WIFI (MS-7C95) – Position: Prompt-Verarbeitung (X) × Ausgabe-Geschwindigkeit (Y), Blasengröße: Anzahl Messläufe. Naeher an der oberen rechten Ecke = schneller.
Processors on this board
Graphics cards on this board
Throughput & latency
In the leaderboard →Performancebenchmark
11 veroeffentlichte Performance-Läufe auf Micro-Star International Co., Ltd. B550M PRO-VDH WIFI (MS-7C95).
| # | Model / Maker | Metrics | Parallel | GPU / CPU / RAM | Runtime | ||
|---|---|---|---|---|---|---|---|
| 1 | Qwen3-Coder-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 400,42 tok/s TG Prefill 12.694 · TTFT 1.086 ms | 5× | NVIDIA GeForce RTX 4090AMD Ryzen 3 3100 4-Core Processor · 61 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 2 | Devstral-Small-2-24B-Instruct-251224BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 265,94 tok/s TG Prefill 8.432 · TTFT 3.619 ms | 10× | NVIDIA GeForce RTX 4090AMD Ryzen 3 3100 4-Core Processor · 61 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 3 | Qwen3-Coder-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 198,88 tok/s TG Prefill 7.188 · TTFT 339 ms | 1× | NVIDIA GeForce RTX 4090AMD Ryzen 3 3100 4-Core Processor · 61 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 4 | Devstral-Small-2-24B-Instruct-251224BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 186,91 tok/s TG Prefill 6.423 · TTFT 2.079 ms | 5× | NVIDIA GeForce RTX 4090AMD Ryzen 3 3100 4-Core Processor · 61 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 5 | Ministral-3-14B-Reasoning-251214BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 157,87 tok/s TG Prefill 8.091 · TTFT 1.495 ms | 5× | NVIDIA GeForce RTX 4090AMD Ryzen 3 3100 4-Core Processor · 61 GB RAM | llama.cppopenclaw_cliQ8_0 | Details → | |
| 6 | Qwen3-Coder-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 68,82 tok/s TG Prefill 3.989 · TTFT 7.885 ms | 10× | NVIDIA GeForce RTX 4090AMD Ryzen 3 3100 4-Core Processor · 61 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 7 | Qwen3-Coder-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 58,29 tok/s TG Prefill 3.005 · TTFT 4.672 ms | 5× | NVIDIA GeForce RTX 4090AMD Ryzen 3 3100 4-Core Processor · 61 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 8 | Ministral-3-14B-Reasoning-251214BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 50,31 tok/s TG Prefill 5.478 · TTFT 413 ms | 1× | NVIDIA GeForce RTX 4090AMD Ryzen 3 3100 4-Core Processor · 61 GB RAM | llama.cppopenclaw_cliQ8_0 | Details → | |
| 9 | Devstral-Small-2-24B-Instruct-251224BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 49,20 tok/s TG Prefill 3.616 · TTFT 593 ms | 1× | NVIDIA GeForce RTX 4090AMD Ryzen 3 3100 4-Core Processor · 61 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 10 | Devstral-Small-2-24B-Instruct-251224BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 49,02 tok/s TG Prefill 3.516 · TTFT 610 ms | 1× | NVIDIA GeForce RTX 4090AMD Ryzen 3 3100 4-Core Processor · 61 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 11 | Qwen3-Coder-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 42,25 tok/s TG Prefill 1.875 · TTFT 1.298 ms | 1× | NVIDIA GeForce RTX 4090AMD Ryzen 3 3100 4-Core Processor · 61 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → |
Agent & chat rating
In the leaderboard →Harnessbenchmark
0 veroeffentlichte Harness-Läufe auf Micro-Star International Co., Ltd. B550M PRO-VDH WIFI (MS-7C95).
Noch keine Harnessbenchmarks auf diesem Mainboard.