Created bymario-alka.dePowered bynoob2claw.detricoma.de
Contributed byMario AlkaMiniMax

MiniMax-M2.5

Performance benchmark · measured on 22.07.2026 19:03

Benchmark-IDrun-20260722-193225-d5f631
Timebench 3 - Kombi (Prefill + Generation)MoE230BRuntime: llama.cppQuantisierung: Q4_K_M
Generation0,84tok/s
Prefill21,52tok/s
Time to First Token98.715,50ms
Total duration600,00s
Concurrency1parallel
Ranking in the field
1873of 1927 systems

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

This run is better than 3 % of all comparable systems.
Generation 0,8 tok/s
-99 % vs Ø 77,5
Prefill 21,5 tok/s
-99 % vs Ø 2.844,6
Time to First Token 98.716 ms
+316 % vs Ø 23.755
Distribution in the field0 – 471 tok/s
Ø 78 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: Keine GPU (CPU-only)
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: Q4_K_M
Model: MiniMax-M2.5

Configuration

benchmark-konfiguration — run-20260722-193225-d5f631
# LLM-Benchmark Konfiguration # Modell : MiniMax-M2.5 # Engine : llama.cpp # Run-ID : run-20260722-193225-d5f631 # GPU : Keine GPU (CPU-only) # 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-M2.5-Q4_K_M/MiniMax-M2.5-Q4_K_M-00001-of-00004.gguf \ -a MiniMax-M2.5 \ --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-M2.5
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-M2.5-Q4_K_M/MiniMax-M2.5-Q4_K_M-00001-of-00004.gguf
Alias?Anzeigename des Modells nach aussen (served model name), unabhaengig vom Dateinamen.MiniMax-M2.5
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
execution_typelocal

All benchmarks of this model To leaderboard

Anzeige
Model comparison

MiniMax-M2.5 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

7165373581790,002.0184.0376.055Prefill (tok/s)Generation (tok/s)NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition - 551,0 tok/s Generation, 4.499 tok/s Prefill, TTFT 9.117 ms (18 Laufe)NVIDIA RTX PRO 6000 B...NVIDIA DGX SPARK (GB10) - 103,5 tok/s Generation, 4.887 tok/s Prefill, TTFT 2.995 ms (3 Laufe)NVIDIA DGX SPARK (GB1...AMD Radeon AI PRO R9700 - 66,1 tok/s Generation, 220 tok/s Prefill, TTFT 98.210 ms (15 Laufe)AMD Radeon AI PRO R97...NVIDIA GeForce RTX 5070 Ti - 22,5 tok/s Generation, 125 tok/s Prefill, TTFT 156.607 ms (6 Laufe)NVIDIA GeForce RTX 50...AMD Radeon PRO W7900 Dual Slot - 19,3 tok/s Generation, 124 tok/s Prefill, TTFT 120.332 ms (12 Laufe)AMD Radeon PRO W7900 ...NVIDIA GeForce RTX 3090 Ti - 15,9 tok/s Generation, 126 tok/s Prefill, TTFT 133.611 ms (6 Laufe)NVIDIA GeForce RTX 30...NVIDIA RTX PRO 6000 Blackwell Workstation Edition - 7,0 tok/s Generation, 83 tok/s Prefill, TTFT 99.522 ms (6 Laufe)NVIDIA RTX PRO 6000 B...NVIDIA GeForce RTX 5090 - 4,4 tok/s Generation, 81 tok/s Prefill, TTFT 88.412 ms (6 Laufe)NVIDIA GeForce RTX 50...AMD Radeon RX 7900 XTX - 4,0 tok/s Generation, 55 tok/s Prefill, TTFT 199.429 ms (3 Laufe)AMD Radeon RX 7900 XTXCPU-only - 0,8 tok/s Generation, 22 tok/s Prefill, TTFT 98.716 ms (1 Lauf) | DIESER LAUF★ CPU-only
NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 551,0 tok/sNVIDIA DGX SPARK (GB10) 103,5 tok/sAMD Radeon AI PRO R9700 66,1 tok/sNVIDIA GeForce RTX 5070 Ti 22,5 tok/sAMD Radeon PRO W7900 Dual Slot 19,3 tok/sNVIDIA GeForce RTX 3090 Ti 15,9 tok/sNVIDIA RTX PRO 6000 Blackwell Workstation Edition 7,0 tok/sNVIDIA GeForce RTX 5090 4,4 tok/sAMD Radeon RX 7900 XTX 4,0 tok/s★ CPU-only 0,8 tok/s this run

CPUby processor

7165373581790,002.0184.0376.055Prefill (tok/s)Generation (tok/s)AMD Ryzen Threadripper PRO 9965WX 24-Cores - 551,0 tok/s Generation, 4.499 tok/s Prefill, TTFT 9.117 ms (18 Laufe)AMD Ryzen Threadrippe...NVIDIA Grace - 103,5 tok/s Generation, 4.887 tok/s Prefill, TTFT 2.995 ms (3 Laufe)NVIDIA GraceAMD Ryzen Threadripper PRO 7955WX 16-Cores - 66,1 tok/s Generation, 220 tok/s Prefill, TTFT 98.210 ms (15 Laufe)AMD Ryzen Threadrippe...AMD Ryzen Threadripper PRO 5975WX 32-Cores - 22,5 tok/s Generation, 124 tok/s Prefill, TTFT 132.424 ms (18 Laufe)AMD Ryzen Threadrippe...AMD Ryzen 9 8945HX with Radeon Graphics - 15,9 tok/s Generation, 126 tok/s Prefill, TTFT 133.611 ms (6 Laufe)AMD Ryzen 9 8945HX wi...AMD Ryzen 9 9950X 16-Core Processor - 7,0 tok/s Generation, 83 tok/s Prefill, TTFT 99.522 ms (6 Laufe)AMD Ryzen 9 9950X 16-...AMD Ryzen 7 5800X3D 8-Core Processor - 4,4 tok/s Generation, 81 tok/s Prefill, TTFT 88.412 ms (6 Laufe)AMD Ryzen 7 5800X3D 8...Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz - 4,0 tok/s Generation, 55 tok/s Prefill, TTFT 199.429 ms (3 Laufe)Intel(R) Xeon(R) CPU ...Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz - 0,8 tok/s Generation, 22 tok/s Prefill, TTFT 98.716 ms (1 Lauf) | DIESER LAUF★ Intel(R) Xeon(R) CPU ...
AMD Ryzen Threadripper PRO 9965WX 24-Cores 551,0 tok/sNVIDIA Grace 103,5 tok/sAMD Ryzen Threadripper PRO 7955WX 16-Cores 66,1 tok/sAMD Ryzen Threadripper PRO 5975WX 32-Cores 22,5 tok/sAMD Ryzen 9 8945HX with Radeon Graphics 15,9 tok/sAMD Ryzen 9 9950X 16-Core Processor 7,0 tok/sAMD Ryzen 7 5800X3D 8-Core Processor 4,4 tok/sIntel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz 4,0 tok/s★ Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz 0,8 tok/s this run

MBby mainboard

7165373581790,002.0174.0346.051Prefill (tok/s)Generation (tok/s)ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE - 551,0 tok/s Generation, 2.554 tok/s Prefill, TTFT 49.613 ms (33 Laufe)ASUSTeK COMPUTER INC....ASUSTeK COMPUTER INC. GX10 - 103,5 tok/s Generation, 4.887 tok/s Prefill, TTFT 2.995 ms (3 Laufe)ASUSTeK COMPUTER INC....ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI - 22,5 tok/s Generation, 124 tok/s Prefill, TTFT 132.424 ms (18 Laufe)ASUSTeK COMPUTER INC....Meigao Innovation Technology (Shen Zhen) Co., Ltd DRFXL (MotherBoard Series) - 15,9 tok/s Generation, 126 tok/s Prefill, TTFT 133.611 ms (6 Laufe)Meigao Innovation Tec...ASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI - 7,0 tok/s Generation, 83 tok/s Prefill, TTFT 99.522 ms (6 Laufe)ASUSTeK COMPUTER INC....ASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING - 4,4 tok/s Generation, 81 tok/s Prefill, TTFT 88.412 ms (6 Laufe)ASUSTeK COMPUTER INC....Dell Inc. PowerEdge R820 - 4,0 tok/s Generation, 47 tok/s Prefill, TTFT 174.251 ms (4 Laufe) | DIESER LAUF★ Dell Inc. PowerEdge R...
ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE 551,0 tok/sASUSTeK COMPUTER INC. GX10 103,5 tok/sASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI 22,5 tok/sMeigao Innovation Technology (Shen Zhen) Co., Ltd DRFXL (MotherBoard Series) 15,9 tok/sASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI 7,0 tok/sASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING 4,4 tok/s★ Dell Inc. PowerEdge R820 4,0 tok/s this run

ENGby engine

6965223481740,08371.5752.3143.053Prefill (tok/s)Generation (tok/s)vLLM - 103,5 tok/s Generation, 2.643 tok/s Prefill, TTFT 22.003 ms (6 Laufe)vLLMllama.cpp - 551,0 tok/s Generation, 1.247 tok/s Prefill, TTFT 93.202 ms (70 Laufe) | DIESER LAUF★ llama.cpp
★ llama.cpp 551,0 tok/s this runvLLM 103,5 tok/s

DRVby driver

6965223481740,02572.1183.9805.841Prefill (tok/s)Generation (tok/s)unbekannt - 551,0 tok/s Generation, 1.212 tok/s Prefill, TTFT 91.057 ms (73 Laufe)unbekanntNVIDIA 590.48.01 / CUDA 13.1 - 103,5 tok/s Generation, 4.887 tok/s Prefill, TTFT 2.995 ms (3 Laufe)NVIDIA 590.48.01 / CU...
unbekannt 551,0 tok/sNVIDIA 590.48.01 / CUDA 13.1 103,5 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 35 W
⚡ TDP 105 W
☁️ External LLM (API)
Electricity0.30 EUR/kWh
Avg power (incl. idle)105 W estimated (TDP)CPU 95 + Board 10 W full load
Avg cost / hourEUR 0.032
Electricity / 1M tokensEUR 10.42
Token / kWh28.80K
Acquisition (system)EUR 2,175 partial priceCPU EUR 39 · RAM EUR 2,016 · PSU EUR 120
Electricity (2 years)–
TCO (2 years)EUR 2,727
Output tokens (2 years)52.98M
☁️ 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 (35 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-M2.5Keine GPU (CPU-only)MiniMax-M2.53x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionMiniMax-M2.53x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionMiniMax-M2.53x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition
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.