MiniMax
MiniMax-M2.7-AWQ-4bit
Performancebenchmark · gemessen am 20.07.2026 11:24
Benchmark-ID
run-20260722-165904-036e47Performancetest Small 1.0MoE230BRuntime: godclawQuantisierung: AWQ
Generation34,37tok/s
Prefill503,09tok/s
Time to First Token105,00ms
Gesamtdauer29,90s
Concurrency1parallel
Einordnung im Feld
64von 135 Systemen
Performancebenchmark · Leitmetrik: Generation-Speed (tok/s)
Dieser Lauf ist besser als 53 % aller vergleichbaren Systeme.
Generation
34,4 tok/s
-19 % vs Ø 42,5
Prefill
503,1 tok/s
-83 % vs Ø 2.885,5
Time to First Token
105 ms
-94 % vs Ø 1.685
Verteilung im Feld2 – 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
MiniMax-M2.7-AWQ-4bit dieser LaufNVIDIA GB10 · run-20260722-165904-036e47
34,4 tok/s
Hardware
GPU: NVIDIA GB10 · 128 GB VRAM
CPU: NVIDIA Grace
RAM: 120 GB
Setup
Runtime: godclaw
Quantisierung: AWQ
Modell: MiniMax-M2.7-AWQ-4bit
Konfiguration
# LLM-Benchmark Konfiguration
# Modell : MiniMax-M2.7-AWQ-4bit
# Engine : vLLM
# Run-ID : run-20260722-165904-036e47
# GPU : NVIDIA GB10
# CPU : NVIDIA Grace
# RAM : 120 GB
bench@llm-benchmark:~$ /usr/bin/python /usr/local/bin/vllm serve cyankiwi/MiniMax-M2.7-AWQ-4bit \
--host 0.0.0.0 \
--port 8000 \
--tensor-parallel-size 2 \
--distributed-executor-backend ray \
--gpu-memory-utilization 0.8 \
--max-model-len 196608 \
--max-num-seqs 4 \
--load-format fastsafetensors \
--tool-call-parser minimax_m2 \
--reasoning-parser minimax_m2 \
--enable-auto-tool-choice \
--kv-cache-dtype fp8_e4m3 \
--enable-prefix-caching \
--trust-remote-code \
--enforce-eager \
--served-model-name cyankiwi/MiniMax-M2.7-AWQ-4bit
| Engine | vllm |
| Modellalias | cyankiwi/MiniMax-M2.7-AWQ-4bit |
| Kontextlaenge | 196608 |
| Tensor-Parallel | 2 |
| Executor-Backend | ray |
| GPU-Speicher | 0.8 |
| Kontext | 196608 |
| Max-Sequenzen | 4 |
| Load-Format | fastsafetensors |
| Tool-Parser | minimax_m2 |
| Reasoning-Parser | minimax_m2 |
| Auto-Tool-Choice | aktiv |
| KV-Cache-Dtype | fp8_e4m3 |
| Prefix-Caching | aktiv |
| Trust-Remote-Code | aktiv |
| Enforce-Eager | aktiv |
| Alias | cyankiwi/MiniMax-M2.7-AWQ-4bit |