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

minimax-m2-awq

Performance benchmark · measured on 28.07.2026 13:27

Benchmark-IDrun-20260728-140955-1a9038
Timebench 3 - Kombi (Prefill + Generation)MoE230BRuntime: llama.cppQuantisierung: UD-Q4_K_M
Generation112,64tok/s
Prefill2.404,79tok/s
Time to First Token972,00ms
Total duration20,14s
Concurrency1parallel
Ranking in the field
398of 1559 systems

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

This run is better than 75 % of all comparable systems.
Generation 112,6 tok/s
+43 % vs Ø 79,0
Prefill 2.404,8 tok/s
-15 % vs Ø 2.834,3
Time to First Token 972 ms
-96 % vs Ø 26.805
Distribution in the field0 – 405 tok/s
Ø 79 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: 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · 96 GB VRAM
CPU: AMD Ryzen Threadripper PRO 9965WX 24-Cores
RAM: 125 GB
Mainboard: ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE

Setup

Runtime: llama.cpp
Quantization: UD-Q4_K_M
Model: minimax-m2-awq

Configuration

benchmark-konfiguration — run-20260728-140955-1a9038
# LLM-Benchmark Konfiguration # Modell : minimax-m2-awq # Engine : llama.cpp # Run-ID : run-20260728-140955-1a9038 # GPU : 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition # CPU : AMD Ryzen Threadripper PRO 9965WX 24-Cores # RAM : 125 GB bench@llm-benchmark:~$ /home/godcore/llama.cpp/build/bin/llama-server \ -m /home/godcore/.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 \ --alias minimax-m2-awq \ --host 0.0.0.0 \ --port 8000 \ -ngl 999 \ -c 16384 \ -np 4 \ --jinja
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-awq
Kontextlaenge?Maximale Anzahl Tokens (Eingabe + erzeugte Ausgabe zusammen), die das Modell pro Anfrage verarbeiten kann.16384
Modellpfad?Pfad zur GGUF-Modelldatei, die geladen und ausgeliefert wird./home/godcore/.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
Kontext?Groesse des Kontextfensters in Token. 0 = der beim Training verwendete Kontext des Modells.16384
np4

All benchmarks of this model To leaderboard

Anzeige
Model comparison

minimax-m2-awq 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

7115333551780,001.6053.2104.815Prefill (tok/s)Generation (tok/s)NVIDIA GeForce RTX 5070 Ti - 17,0 tok/s Generation, 100 tok/s Prefill, TTFT 162.821 ms (3 Laufe)NVIDIA GeForce RTX 50...NVIDIA RTX PRO 6000 Blackwell Workstation Edition - 8,7 tok/s Generation, 80 tok/s Prefill, TTFT 91.651 ms (3 Laufe)NVIDIA RTX PRO 6000 B...NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition - 547,9 tok/s Generation, 3.894 tok/s Prefill, TTFT 9.312 ms (3 Laufe) | DIESER LAUF★ NVIDIA RTX PRO 6000 B...
★ NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 547,9 tok/s this runNVIDIA GeForce RTX 5070 Ti 17,0 tok/sNVIDIA RTX PRO 6000 Blackwell Workstation Edition 8,7 tok/s

CPUby processor

7115333551780,001.6053.2104.815Prefill (tok/s)Generation (tok/s)AMD Ryzen Threadripper PRO 5975WX 32-Cores - 17,0 tok/s Generation, 100 tok/s Prefill, TTFT 162.821 ms (3 Laufe)AMD Ryzen Threadrippe...AMD Ryzen 9 9950X 16-Core Processor - 8,7 tok/s Generation, 80 tok/s Prefill, TTFT 91.651 ms (3 Laufe)AMD Ryzen 9 9950X 16-...AMD Ryzen Threadripper PRO 9965WX 24-Cores - 547,9 tok/s Generation, 3.894 tok/s Prefill, TTFT 9.312 ms (3 Laufe) | DIESER LAUF★ AMD Ryzen Threadrippe...
★ AMD Ryzen Threadripper PRO 9965WX 24-Cores 547,9 tok/s this runAMD Ryzen Threadripper PRO 5975WX 32-Cores 17,0 tok/sAMD Ryzen 9 9950X 16-Core Processor 8,7 tok/s

MBby mainboard

7115333551780,001.6053.2104.815Prefill (tok/s)Generation (tok/s)ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI - 17,0 tok/s Generation, 100 tok/s Prefill, TTFT 162.821 ms (3 Laufe)ASUSTeK COMPUTER INC....ASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI - 8,7 tok/s Generation, 80 tok/s Prefill, TTFT 91.651 ms (3 Laufe)ASUSTeK COMPUTER INC....ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE - 547,9 tok/s Generation, 3.894 tok/s Prefill, TTFT 9.312 ms (3 Laufe) | DIESER LAUF★ ASUSTeK COMPUTER INC....
★ ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE 547,9 tok/s this runASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI 17,0 tok/sASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI 8,7 tok/s

ENGby engine

6035755485204931.2761.3311.3851.439Prefill (tok/s)Generation (tok/s)llama.cpp - 547,9 tok/s Generation, 1.358 tok/s Prefill, TTFT 87.928 ms (9 Laufe) | DIESER LAUF★ llama.cpp
★ llama.cpp 547,9 tok/s this run

DRVby driver

6035755485204931.2761.3311.3851.439Prefill (tok/s)Generation (tok/s)unbekannt - 547,9 tok/s Generation, 1.358 tok/s Prefill, TTFT 87.928 ms (9 Laufe)unbekannt
unbekannt 547,9 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 165 W
⚡ TDP 983 W
☁️ External LLM (API)
Electricity0.30 EUR/kWh
Avg power (incl. idle)983 W estimated (TDP)GPU 900 + CPU 57 + Board 25 W full load
Avg cost / hourEUR 0.29
Electricity / 1M tokensEUR 0.73
Token / kWh412.73K
Acquisition (system)EUR 45,748 full priceGPU EUR 39,000 · CPU EUR 3,499 · Board EUR 1,299 · RAM EUR 1,750 · PSU EUR 200
Electricity (2 years)
TCO (2 years)EUR 50,912
Output tokens (2 years)7.10B
☁️ 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 (165 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-awq3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Editionminimax-m2-awqNVIDIA GeForce RTX 5070 Timinimax-m2-awqNVIDIA RTX PRO 6000 Blackwell 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.