Cohere
command-a-reasoning-08-2025
Performancebenchmark · gemessen am 22.07.2026 20:51
Benchmark-ID
run-20260722-190202-a4102bTimebench 3 - Kombi (Prefill + Generation)Runtime: llama.cppQuantisierung: Q4_K_M
Generation7,81tok/s
Prefill172,95tok/s
Time to First Token10.910,00ms
Gesamtdauer59,99s
Concurrency1parallel
Einordnung im Feld
124von 140 Systemen
Performancebenchmark · Leitmetrik: Generation-Speed (tok/s)
Dieser Lauf ist besser als 12 % aller vergleichbaren Systeme.
Generation
7,8 tok/s
-81 % vs Ø 41,1
Prefill
173,0 tok/s
-94 % vs Ø 2.784,3
Time to First Token
10.910 ms
+243 % vs Ø 3.177
Verteilung im Feld1 – 148 tok/s
Wie schlägt sich dieser Benchmark?
gpt-oss-20b3× AMD Radeon AI PRO R9700 · run-20260722-165909-85f64f
147,8 tok/s
gpt-oss-20b3× AMD Radeon AI PRO R9700 · run-20260722-165909-637af7
143,9 tok/s
gpt-oss-20b3× AMD Radeon AI PRO R9700 · run-20260722-165909-65d35f
137,7 tok/s
Nemotron-Cascade-2-30B-A3B3× AMD Radeon AI PRO R9700 · run-20260722-181156-a273f2
107,9 tok/s
Nemotron-3-Nano-Omni-30B-A3B-Reasoning3× AMD Radeon AI PRO R9700 · run-20260722-182228-95c528
102,9 tok/s
gpt-oss-120b3× AMD Radeon AI PRO R9700 · run-20260722-165909-4e3ede
99,8 tok/s
Qwen3-30B-A3B-Instruct-25073× AMD Radeon AI PRO R9700 · run-20260722-165907-cc8f3f
97,6 tok/s
NVIDIA-Nemotron-3-Nano-4B3× AMD Radeon AI PRO R9700 · run-20260722-190202-45dc8e
93,4 tok/s
Qwen3-30B-A3B-Thinking-25073× AMD Radeon AI PRO R9700 · run-20260722-165908-5712c8
91,4 tok/s
Qwen3-30B-A3B-Instruct-25073× AMD Radeon AI PRO R9700 · run-20260722-165907-b20fe5
91,0 tok/s
Qwen3-VL-30B-A3B-Instruct3× AMD Radeon AI PRO R9700 · run-20260722-165908-4d91c3
89,8 tok/s
Qwen3-30B-A3B-Thinking-25073× AMD Radeon AI PRO R9700 · run-20260722-165908-40e052
88,6 tok/s
Qwen3-Coder-30B-A3B-Instruct3× AMD Radeon AI PRO R9700 · run-20260722-165907-0a4b43
88,2 tok/s
Qwen3-30B-A3B-Thinking-25073× AMD Radeon AI PRO R9700 · run-20260722-165907-83951d
87,8 tok/s
command-a-reasoning-08-2025 dieser Lauf3× AMD Radeon AI PRO R9700 · run-20260722-190202-a4102b
7,8 tok/s
Hardware
GPU: 3x AMD Radeon AI PRO R9700 · 32 GB VRAM
CPU: 32x AMD Ryzen Threadripper PRO 7955WX 16-Cores
RAM: 184 GB
Setup
Runtime: llama.cpp
Quantisierung: Q4_K_M
Modell: command-a-reasoning-08-2025
Konfiguration
# LLM-Benchmark Konfiguration
# Modell : command-a-reasoning-08-2025
# Engine : llama.cpp
# Run-ID : run-20260722-190202-a4102b
# GPU : 3x AMD Radeon AI PRO R9700
# CPU : 32x AMD Ryzen Threadripper PRO 7955WX 16-Cores
# RAM : 184 GB
bench@llm-benchmark:~$ /src/build/bin/llama-server \
-m /root/.cache/huggingface/hub/models--DevQuasar--CohereLabs.command-a-reasoning-08-2025-GGUF/snapshots/924408415a0e807b935d0a0c4f316a1bc40a1051/CohereLabs.command-a-reasoning-08-2025.Q4_K_M-00001-of-00005.gguf \
-ngl 999 \
-c 8192 \
-a command-a-reasoning-08-2025 \
-sm layer \
--host 0.0.0.0 \
--port 8000
| Engine | llamacpp |
| Modellalias | command-a-reasoning-08-2025 |
| Kontextlaenge | 8192 |
| Modellpfad | /root/.cache/huggingface/hub/models--DevQuasar--CohereLabs.command-a-reasoning-08-2025-GGUF/snapshots/924408415a0e807b935d0a0c4f316a1bc40a1051/CohereLabs.command-a-reasoning-08-2025.Q4_K_M-00001-of-00005.gguf |
| GPU-Layer | 999 |
| Kontext | 8192 |
| Alias | command-a-reasoning-08-2025 |
| Split-Mode | layer |