Contributed byMario AlkaMiniMax MiniMax-M2.7
Performance benchmark · measured on 22.07.2026 09:05
Benchmark-ID
run-20260722-165909-758b3bMoE230BRuntime: godclawQuantisierung: Q4_K_M
Generation3,00tok/s
Prefill139,37tok/s
Time to First Token15.492,50ms
Total duration99,67s
Concurrency1parallel
Ranking in the field
1026of 1161 systems
Performance benchmark · Primary metric: Generation-Speed (tok/s) · 1× concurrent
This run is better than 12 % of all comparable systems.
Generation
3,0 tok/s
-96 % vs Ø 74,3
Prefill
139,4 tok/s
-94 % vs Ø 2.324,7
Time to First Token
15.493 ms
-57 % vs Ø 35.657
Distribution in the field0 – 405 tok/s
Wie schlägt sich dieser Benchmark mit anderen Modellen?
gpt-oss-20bNVIDIA GeForce RTX 5090 · run-20260724-004608-16af9b
404,6 tok/s
gpt-oss-20bNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260730-035052-9f766a
395,2 tok/s
Nemotron-3-Nano-4BNVIDIA GeForce RTX 5090 · run-20260728-194135-d456e7
393,5 tok/s
Nemotron-3-Nano-4BNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260727-181607-bffb11
393,5 tok/s
gpt-oss-20bNVIDIA GeForce RTX 5090 · run-20260724-004607-29bd16
388,9 tok/s
gpt-oss-20bNVIDIA GeForce RTX 5090 · run-20260729-032121-1c779f
388,2 tok/s
gemma-4-E2B-itNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260727-181606-6ea089
378,6 tok/s
gemma-4-E2B-itNVIDIA GeForce RTX 5090 · run-20260728-184455-e8b129
377,6 tok/s
Nemotron-3-Nano-4B3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-194136-ac388e
362,3 tok/s
Nemotron-3-Nano-4B3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-194136-5e5085
361,4 tok/s
Nemotron-3-Nano-30B-A3BNVIDIA GeForce RTX 5090 · run-20260729-105335-653788
359,4 tok/s
Nemotron-3-Nano-Omni-30B-A3B-ReasoningNVIDIA GeForce RTX 5090 · run-20260729-105334-2c4905
359,3 tok/s
Nemotron-Cascade-2-30B-A3BNVIDIA GeForce RTX 5090 · run-20260729-105334-44d1e7
359,0 tok/s
Nemotron-3-Nano-Omni-30B-A3B-ReasoningNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260729-032119-4852bf
357,1 tok/s
MiniMax-M2.7 this run3× AMD Radeon AI PRO R9700 · run-20260722-165909-758b3b
3,0 tok/s
How does this benchmark compare on other GPUs?
Same model on different hardware · 1× concurrent · Generation (tok/s)
3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Editionrun-20260806-094434-358a5d
112,8 tok/s
3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Editionrun-20260806-094434-e88b45
112,6 tok/s
NVIDIA GB10run-20260722-165904-036e47
34,4 tok/s
NVIDIA GB10run-20260723-055735-60de93
31,5 tok/s
NVIDIA GB10run-20260726-091400-f470fb
29,4 tok/s
NVIDIA GB10run-20260726-084121-cde663
24,3 tok/s
NVIDIA GB10run-20260726-084121-98ddc2
24,0 tok/s
3× AMD Radeon AI PRO R9700run-20260806-094438-f664b5
9,0 tok/s
3× AMD Radeon AI PRO R9700run-20260806-094438-cfda1f
9,0 tok/s
3× AMD Radeon AI PRO R9700run-20260806-094438-e40031
9,0 tok/s
3× AMD Radeon AI PRO R9700run-20260726-084121-1490ea
7,1 tok/s
NVIDIA RTX PRO 6000 Blackwell Workstation Editionrun-20260806-094439-70a150
5,2 tok/s
NVIDIA GeForce RTX 3090 Tirun-20260730-120419-2ad3a7
4,0 tok/s
NVIDIA GeForce RTX 5090run-20260806-094439-50d485
3,3 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
Mainboard: ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE
Setup
Runtime: godclaw
Quantization: Q4_K_M
Operating system: Ubuntu 26.04 LTS (Kernel 7.0.0-27-generic)
Driver: AMD 7.0.0-27-generic
Model: MiniMax-M2.7
Anmerkung
llama.cpp . 3 GPU . GGUF (unsloth/MiniMax-M2.7-GGUF) . RAM-Offload -cmoe (~230B MoE)
Configuration
# LLM-Benchmark Konfiguration
# Modell : MiniMax-M2.7
# Run-ID : run-20260722-165909-758b3b
# GPU : 3x AMD Radeon AI PRO R9700
# CPU : 32x AMD Ryzen Threadripper PRO 7955WX 16-Cores
# RAM : 184 GB
bench@llm-benchmark:~$ cat benchmark.conf
Konfigurationspfad /root/.cache/huggingface/hub/models--unsloth--MiniMax-M2.7-GGUF/snapshots/d2a05ccf69491b03db0cc40b335aec14bdaf7198/UD-Q4_K_M/MiniMax-M2.7-UD-Q4_K_M-00001-of-00004.gguf
Engine llamacpp
Modellalias MiniMax-M2.7
Kontextlaenge 8192
GPU-Layer 999
cmoe aktiv
Split-Mode layer
Host 0.0.0.0
Port 8000
| Engine?Die Inferenz-Software, die das Modell ausliefert (z.B. vLLM oder llama.cpp). Sie bestimmt Geschwindigkeit, unterstuetzte Modellformate und welche Parameter ueberhaupt verfuegbar sind. | llamacpp |
| Modellalias?Der Name, unter dem das Modell ueber die API angesprochen wird. Genau dieser Wert muss im Request-Feld 'model' stehen. | MiniMax-M2.7 |
| Kontextlaenge?Maximale Anzahl Tokens (Eingabe + erzeugte Ausgabe zusammen), die das Modell pro Anfrage verarbeiten kann. | 8192 |
| Modellpfad?Pfad zur GGUF-Modelldatei, die geladen und ausgeliefert wird. | /root/.cache/huggingface/hub/models--unsloth--MiniMax-M2.7-GGUF/snapshots/d2a05ccf69491b03db0cc40b335aec14bdaf7198/UD-Q4_K_M/MiniMax-M2.7-UD-Q4_K_M-00001-of-00004.gguf |
| GPU-Layer?Anzahl der auf die GPU ausgelagerten Modell-Layer. Hoeher = mehr VRAM und schneller; der Rest laeuft auf der CPU. 999 = alles auf GPU. | 999 |
| cmoe | aktiv |
| Kontext?Groesse des Kontextfensters in Token. 0 = der beim Training verwendete Kontext des Modells. | 8192 |
| Alias?Anzeigename des Modells nach aussen (served model name), unabhaengig vom Dateinamen. | MiniMax-M2.7 |
| Split-Mode?Verteilung ueber mehrere GPUs: none (nur eine GPU), layer (Layer aufteilen) oder row (Tensoren zeilenweise). | layer |
| Host?Netzwerk-Interface, an das der HTTP-Server bindet, z.B. 0.0.0.0 fuer alle Interfaces. | 0.0.0.0 |
| Port?TCP-Port des HTTP-Servers. | 8000 |
Anzeige
Videoreihe und Benchmarkauswertung zur AMD R9700
Model comparison
MiniMax-M2.7 on various hardware
All published performance runs of this model – each bubble a variant: position = prefill (X) × generation (Y), bubble size = number of runs. Closer to the top right = faster. ★ Marked gold = this benchmark.
GPUby graphics card
CPUby processor
AMD Ryzen Threadripper PRO 9965WX 24-Cores 548,6 tok/sNVIDIA Grace 174,2 tok/s★ AMD Ryzen Threadripper PRO 7955WX 16-Cores 14,5 tok/s this runAMD Ryzen 9 9950X 16-Core Processor 7,0 tok/sAMD Ryzen 7 5800X3D 8-Core Processor 6,0 tok/sAMD Ryzen 9 8945HX with Radeon Graphics 4,0 tok/sIntel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz 2,6 tok/s
MBby mainboard
★ ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE 548,6 tok/s this runASUSTeK COMPUTER INC. GX10 174,2 tok/sASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI 7,0 tok/sASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING 6,0 tok/sMeigao Innovation Technology (Shen Zhen) Co., Ltd DRFXL (MotherBoard Series) 4,0 tok/sDell Inc. PowerEdge R820 2,6 tok/s
DRVby driver
unbekannt 548,6 tok/sNVIDIA 590.48.01 / CUDA 13.1 174,2 tok/s★ AMD 7.0.0-27-generic 3,0 tok/s this run
💰 Economics
Economics of this run
Operating cost, TCO and comparison with the next-best runs of the same model at identical concurrency (1× concurrent). Methodology →
⚙️ ConfigurationAll metrics and charts below follow these settings – based on a 24-month runtime.Save to URLReset
⚡ Electricity price
EUR/kWh
⚙️ System utilization
100 %
🖥️ Acquisition
EUR
🔌 Idle
125 W
⚡ TDP
971 W
☁️ External LLM (API)
Electricity0.30 EUR/kWh
Avg power (incl. idle)971 W estimated (TDP)GPU 900 + CPU 46 + Board 25 W full load
Avg cost / hourEUR 0.29
Electricity / 1M tokensEUR 26.97
Token / kWh11.12K
Acquisition (system)EUR 9,674 full priceGPU EUR 4,200 · CPU EUR 1,399 · Board EUR 1,299 · RAM EUR 2,576 · PSU EUR 200
Electricity (2 years)–
TCO (2 years)EUR 14,778
Output tokens (2 years)189.22M
☁️ External LLM (API) – comparison
External LLM cost (2 years)–
Savings vs. external (2 years)–
All values above and the charts below take the configured system utilization into account: at X% the system generates only X% of the time, the rest it idles (125 W). Cost per hour drops (more idle), cost per token rises.
Cost over 2 years – electricity only
Cost over 2 years – incl. acquisition (TCO)
Speed vs. tokens per euro
Euro per 1M tokens
Comparison vs. API – economics per benchmark
| MiniMax-M2.73x AMD Radeon AI PRO R9700 | MiniMax-M2.73x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition | MiniMax-M2.73x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition | MiniMax-M2.7NVIDIA GB10 (DGX Spark) | |
|---|---|---|---|---|
| Electricity cost (24 mo.) | – | – | – | – |
| Acquisition cost | – | – | – | – |
| Total cost (TCO) | – | – | – | – |
| Generated tokens (24 mo.) | – | – | – | – |
| Token price via API | – | – | – | – |
| Break-even point (days) | – | – | – | – |
| Result (savings / extra cost) | – | – | – | – |
3× AMD Radeon AI PRO R9700 · this run 3 tok/s3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 113 tok/s3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 113 tok/sNVIDIA GB10 (DGX Spark) 34 tok/s
Comparison with up to 3 next-best runs of this model at the same concurrency (at least one on different hardware). Power = GPU TDP + CPU (idle + 15 %) + board (estimated), acquisition = full system (GPU + CPU + board + RAM + PSU), prices = stored market prices.
Contributed by
Mario Alka Administrator
@marioalka
Ich bin Unternehmer, Softwareentwickler und KI-Enthusiast. Seit vielen Jahren entwickle ich Unternehmenssoftware und beschäftige mich inzwischen fast täglich mit lokalen LLMs, KI-Agenten und leistungsfähiger KI-Hardware.
Mit LLM-Benchmark.de möchte ich eine Plattform schaffen, auf der Modelle, GPUs und Agenten objektiv und reproduzierbar miteinander verglichen werden.