Created bymario-alka.dePowered bygodcore.denoob2claw.detricoma.de
Contributed byMario AlkaMiniMax

MiniMax-M2.7

Performance benchmark · measured on 23.07.2026 09:12

Benchmark-IDrun-20260723-114454-a888a9
Timebench 3 - Kombi (Prefill + Generation)MoE230BRuntime: llama.cppQuantisierung: UD-Q4_K_M
Generation2,62tok/s
Prefill14,77tok/s
Time to First Token156.049,50ms
Total duration600,00s
Concurrency1parallel
Ranking in the field
27of 33 systems

Performance benchmark · Primary metric: Generation-Speed (tok/s) · 1× concurrent

This run is better than 19 % of all comparable systems.
Generation 2,6 tok/s
-88 % vs Ø 21,9
Prefill 14,8 tok/s
-98 % vs Ø 605,3
Time to First Token 156.050 ms
+249 % vs Ø 44.665
Distribution in the field1 – 81 tok/s
Ø 22 Median Dieser Lauf

Wie schlägt sich dieser Benchmark mit anderen Modellen?

How does this benchmark compare on other GPUs?

Same model on different hardware · 1× concurrent · Generation (tok/s)

Hardware

GPU: 2x NVIDIA GeForce RTX 2060 · 6 GB VRAM
CPU: 4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz
RAM: 504 GB
Mainboard: Dell Inc. PowerEdge R820

Setup

Runtime: llama.cpp
Quantization: UD-Q4_K_M
Model: MiniMax-M2.7

Configuration

benchmark-konfiguration — run-20260723-114454-a888a9
# LLM-Benchmark Konfiguration # Modell : MiniMax-M2.7 # Engine : llama.cpp # Run-ID : run-20260723-114454-a888a9 # GPU : 2x NVIDIA GeForce RTX 2060 # CPU : 4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz # RAM : 504 GB bench@llm-benchmark:~$ /opt/llama.cpp/build/bin/llama-server \ -m /opt/models/MiniMax-M2.7-Q4_K_M/MiniMax-M2.7-Q4_K_M-00001-of-00004.gguf \ -a MiniMax-M2.7 \ --host 0.0.0.0 \ --port 8080 \ --numa distribute \ -t 64 \ -tb 64 \ -c 8192 \ --parallel 4
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./opt/models/MiniMax-M2.7-Q4_K_M/MiniMax-M2.7-Q4_K_M-00001-of-00004.gguf
Alias?Anzeigename des Modells nach aussen (served model name), unabhaengig vom Dateinamen.MiniMax-M2.7
NUMA?NUMA-Optimierung fuer Multi-Socket-CPUs: distribute/isolate/numactl. Verbessert die Speicherlokalitaet.distribute
Threads?Anzahl CPU-Threads fuer die Token-Generierung (Decode).64
Batch-Threads?Anzahl CPU-Threads fuer Prompt-Verarbeitung und Batch (Prefill).64
Kontext?Groesse des Kontextfensters in Token. 0 = der beim Training verwendete Kontext des Modells.8192
Parallel?Anzahl paralleler Slots/Sequenzen, die der Server gleichzeitig bedient. Der Kontext wird auf die Slots aufgeteilt.4

All benchmarks of this model To leaderboard

Anzeige
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

7135353561780,001.7803.5615.341Prefill (tok/s)Generation (tok/s)NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition - 548,6 tok/s Generation, 3.645 tok/s Prefill, TTFT 9.650 ms (6 Laufe)NVIDIA RTX PRO 6000 B...NVIDIA GB10 (DGX Spark) - 174,2 tok/s Generation, 4.309 tok/s Prefill, TTFT 7.582 ms (13 Laufe)NVIDIA GB10 (DGX Spar...AMD Radeon AI PRO R9700 - 14,5 tok/s Generation, 187 tok/s Prefill, TTFT 92.001 ms (14 Laufe)AMD Radeon AI PRO R97...NVIDIA RTX PRO 6000 Blackwell Workstation Edition - 7,0 tok/s Generation, 84 tok/s Prefill, TTFT 98.659 ms (5 Laufe)NVIDIA RTX PRO 6000 B...NVIDIA GeForce RTX 5090 - 6,0 tok/s Generation, 66 tok/s Prefill, TTFT 126.812 ms (5 Laufe)NVIDIA GeForce RTX 50...NVIDIA GeForce RTX 3090 Ti - 4,0 tok/s Generation, 10 tok/s Prefill, TTFT 346.143 ms (3 Laufe)NVIDIA GeForce RTX 30...NVIDIA GeForce RTX 2060 - 2,6 tok/s Generation, 24 tok/s Prefill, TTFT 193.311 ms (3 Laufe) | DIESER LAUF★ NVIDIA GeForce RTX 20...
NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 548,6 tok/sNVIDIA GB10 (DGX Spark) 174,2 tok/sAMD Radeon AI PRO R9700 14,5 tok/sNVIDIA RTX PRO 6000 Blackwell Workstation Edition 7,0 tok/sNVIDIA GeForce RTX 5090 6,0 tok/sNVIDIA GeForce RTX 3090 Ti 4,0 tok/s★ NVIDIA GeForce RTX 2060 2,6 tok/s this run

CPUby processor

7135353561780,001.7803.5615.341Prefill (tok/s)Generation (tok/s)AMD Ryzen Threadripper PRO 9965WX 24-Cores - 548,6 tok/s Generation, 3.645 tok/s Prefill, TTFT 9.650 ms (6 Laufe)AMD Ryzen Threadrippe...NVIDIA Grace - 174,2 tok/s Generation, 4.309 tok/s Prefill, TTFT 7.582 ms (13 Laufe)NVIDIA GraceAMD Ryzen Threadripper PRO 7955WX 16-Cores - 14,5 tok/s Generation, 187 tok/s Prefill, TTFT 92.001 ms (14 Laufe)AMD Ryzen Threadrippe...AMD Ryzen 9 9950X 16-Core Processor - 7,0 tok/s Generation, 84 tok/s Prefill, TTFT 98.659 ms (5 Laufe)AMD Ryzen 9 9950X 16-...AMD Ryzen 7 5800X3D 8-Core Processor - 6,0 tok/s Generation, 66 tok/s Prefill, TTFT 126.812 ms (5 Laufe)AMD Ryzen 7 5800X3D 8...AMD Ryzen 9 8945HX with Radeon Graphics - 4,0 tok/s Generation, 10 tok/s Prefill, TTFT 346.143 ms (3 Laufe)AMD Ryzen 9 8945HX wi...Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz - 2,6 tok/s Generation, 24 tok/s Prefill, TTFT 193.311 ms (3 Laufe) | DIESER LAUF★ Intel(R) Xeon(R) CPU ...
AMD Ryzen Threadripper PRO 9965WX 24-Cores 548,6 tok/sNVIDIA Grace 174,2 tok/sAMD Ryzen Threadripper PRO 7955WX 16-Cores 14,5 tok/sAMD 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/s★ Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz 2,6 tok/s this run

MBby mainboard

7135353561780,001.7803.5615.341Prefill (tok/s)Generation (tok/s)ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE - 548,6 tok/s Generation, 1.224 tok/s Prefill, TTFT 67.296 ms (20 Laufe)ASUSTeK COMPUTER INC....ASUSTeK COMPUTER INC. GX10 - 174,2 tok/s Generation, 4.309 tok/s Prefill, TTFT 7.582 ms (13 Laufe)ASUSTeK COMPUTER INC....ASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI - 7,0 tok/s Generation, 84 tok/s Prefill, TTFT 98.659 ms (5 Laufe)ASUSTeK COMPUTER INC....ASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING - 6,0 tok/s Generation, 66 tok/s Prefill, TTFT 126.812 ms (5 Laufe)ASUSTeK COMPUTER INC....Meigao Innovation Technology (Shen Zhen) Co., Ltd DRFXL (MotherBoard Series) - 4,0 tok/s Generation, 10 tok/s Prefill, TTFT 346.143 ms (3 Laufe)Meigao Innovation Tec...Dell Inc. PowerEdge R820 - 2,6 tok/s Generation, 24 tok/s Prefill, TTFT 193.311 ms (3 Laufe) | DIESER LAUF★ Dell Inc. PowerEdge R...
ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE 548,6 tok/sASUSTeK 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/s★ Dell Inc. PowerEdge R820 2,6 tok/s this run

ENGby engine

7135343561780,001.4802.9594.439Prefill (tok/s)Generation (tok/s)vLLM - 174,2 tok/s Generation, 3.600 tok/s Prefill, TTFT 10.381 ms (16 Laufe)vLLMunbekannt - 3,0 tok/s Generation, 139 tok/s Prefill, TTFT 15.493 ms (1 Lauf)unbekanntllama.cpp - 548,6 tok/s Generation, 738 tok/s Prefill, TTFT 125.269 ms (32 Laufe) | DIESER LAUF★ llama.cpp
★ llama.cpp 548,6 tok/s this runvLLM 174,2 tok/sunbekannt 3,0 tok/s

DRVby driver

7135343561780,001.7733.5455.318Prefill (tok/s)Generation (tok/s)unbekannt - 548,6 tok/s Generation, 720 tok/s Prefill, TTFT 116.461 ms (35 Laufe)unbekanntNVIDIA 590.48.01 / CUDA 13.1 - 174,2 tok/s Generation, 4.309 tok/s Prefill, TTFT 7.582 ms (13 Laufe)NVIDIA 590.48.01 / CU...AMD 7.0.0-27-generic - 3,0 tok/s Generation, 139 tok/s Prefill, TTFT 15.493 ms (1 Lauf)AMD 7.0.0-27-generic
unbekannt 548,6 tok/sNVIDIA 590.48.01 / CUDA 13.1 174,2 tok/sAMD 7.0.0-27-generic 3,0 tok/s
💰 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 55 W
⚡ TDP 359 W
☁️ External LLM (API)
Electricity0.30 EUR/kWh
Avg power (incl. idle)359 W estimated (TDP)GPU 320 + CPU 29 + Board 10 W full load
Avg cost / hourEUR 0.11
Electricity / 1M tokensEUR 11.41
Token / kWh26.29K
Acquisition (system)EUR 2,425 partial priceGPU EUR 220 · CPU EUR 39 · RAM EUR 2,016 · PSU EUR 150
Electricity (2 years)
TCO (2 years)EUR 4,311
Output tokens (2 years)165.25M
☁️ 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 (55 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-M2.72x NVIDIA GeForce RTX 2060MiniMax-M2.73x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionMiniMax-M2.73x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionMiniMax-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)

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.