Contributed byMario AlkaMiniMax MiniMax-M2.5
Performance benchmark · measured on 22.07.2026 13:15
Benchmark-ID
run-20260722-165909-cbdb29MoE230BRuntime: godclaw
Generation6,46tok/s
Prefill119,37tok/s
Time to First Token21.345,50ms
Total duration178,63s
Concurrency1parallel
Ranking in the field
375of 455 systems
Performance benchmark · Primary metric: Generation-Speed (tok/s) · 1× concurrent
This run is better than 17 % of all comparable systems.
Generation
6,5 tok/s
-82 % vs Ø 35,3
Prefill
119,4 tok/s
-94 % vs Ø 1.966,4
Time to First Token
21.346 ms
-40 % vs Ø 35.848
Distribution in the field1 – 148 tok/s
Wie schlägt sich dieser Benchmark mit anderen Modellen?
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-20260722-165908-d95290
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-20260722-165908-95273d
143,9 tok/s
Nemotron-3-Nano-4B3× AMD Radeon AI PRO R9700 · run-20260805-053357-112090
139,8 tok/s
gpt-oss-20b3× AMD Radeon AI PRO R9700 · run-20260722-165909-65d35f
137,7 tok/s
gpt-oss-20b3× AMD Radeon AI PRO R9700 · run-20260722-165908-ff206d
137,7 tok/s
Nemotron-3-Nano-4B3× AMD Radeon AI PRO R9700 · run-20260805-053357-ed67ec
136,2 tok/s
Nemotron-3-Nano-4B3× AMD Radeon AI PRO R9700 · run-20260805-053357-16d611
129,5 tok/s
Nemotron-3-Nano-30B-A3B4× AMD Radeon AI PRO R9700 · run-20260817-111922-dd07f5
125,7 tok/s
Nemotron-3.5-Lightning-30B-A3B4× AMD Radeon AI PRO R9700 · run-20260815-060242-025c3d
121,3 tok/s
Nemotron-3.5-Lightning-30B-A3B4× AMD Radeon AI PRO R9700 · run-20260815-060242-dadb7a
113,6 tok/s
Nemotron-3.5-Lightning-30B-A3B4× AMD Radeon AI PRO R9700 · run-20260815-060243-6a7849
108,1 tok/s
Nemotron-Cascade-2-30B-A3B3× AMD Radeon AI PRO R9700 · run-20260722-181156-a273f2
107,9 tok/s
MiniMax-M2.5 this run3× AMD Radeon AI PRO R9700 · run-20260722-165909-cbdb29
6,5 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-20260729-032130-3a3cc6
116,2 tok/s
3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Editionrun-20260728-164528-2c7f40
116,2 tok/s
3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Editionrun-20260729-032127-fd7165
116,2 tok/s
3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Editionrun-20260728-164528-176d92
115,7 tok/s
3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Editionrun-20260729-032127-0f36ce
109,0 tok/s
3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Editionrun-20260729-032129-05f4c7
106,9 tok/s
3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Editionrun-20260722-165903-309484
62,7 tok/s
3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Editionrun-20260722-165904-a1f0cb
62,7 tok/s
NVIDIA GB10run-20260726-091400-b10991
32,2 tok/s
NVIDIA GB10run-20260726-084120-94f03f
31,9 tok/s
4× AMD Radeon AI PRO R9700run-20260810-003948-22d7b0
28,4 tok/s
2× AMD Radeon PRO W7900 Dual Slotrun-20260818-094144-d89c6b
14,6 tok/s
AMD Radeon PRO W7900 Dual Slotrun-20260817-222755-979828
14,5 tok/s
NVIDIA GeForce RTX 5070 Tirun-20260728-164527-55ef81
11,9 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: -
Operating system: Ubuntu 26.04 LTS (Kernel 7.0.0-27-generic)
Driver: AMD 7.0.0-27-generic
Model: MiniMax-M2.5
Anmerkung
llama.cpp . 3 GPU . GGUF (ubergarm/MiniMax-M2.5-GGUF IQ4_NL) . RAM-Offload -cmoe
Configuration
# LLM-Benchmark Konfiguration
# Modell : MiniMax-M2.5
# Run-ID : run-20260722-165909-cbdb29
# 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--ubergarm--MiniMax-M2.5-GGUF/snapshots/6e9d9db189e9c7d70ed222ea823c20dd3e5d980e/mainline-IQ4_NL/MiniMax-M2.5-mainline-IQ4_NL-00001-of-00004.gguf
Engine llamacpp
Modellalias Minimax-2.5
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-2.5 |
| 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. | /root/.cache/huggingface/hub/models--ubergarm--MiniMax-M2.5-GGUF/snapshots/6e9d9db189e9c7d70ed222ea823c20dd3e5d980e/mainline-IQ4_NL/MiniMax-M2.5-mainline-IQ4_NL-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-2.5 |
| 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-M2.5 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
NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 551,0 tok/sNVIDIA GB10 (DGX Spark) 105,6 tok/s★ AMD Radeon AI PRO R9700 66,1 tok/s this runNVIDIA 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/sCPU-only 0,8 tok/s
CPUby processor
AMD Ryzen Threadripper PRO 9965WX 24-Cores 551,0 tok/sNVIDIA Grace 105,6 tok/s★ AMD Ryzen Threadripper PRO 7955WX 16-Cores 66,1 tok/s this runAMD 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 E5-4620 v2 @ 2.60GHz 0,8 tok/s
MBby mainboard
★ ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE 551,0 tok/s this runASUSTeK COMPUTER INC. GX10 105,6 tok/sunbekannt 62,7 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/sDell Inc. PowerEdge R820 0,8 tok/s
DRVby driver
unbekannt 551,0 tok/sNVIDIA 590.48.01 / CUDA 13.1 105,6 tok/sNVIDIA 580.159.04 / CUDA 13.0 62,7 tok/s★ AMD 7.0.0-27-generic 6,5 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 12.53
Token / kWh23.95K
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)407.45M
☁️ 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-M2.53x AMD Radeon AI PRO R9700 | MiniMax-M2.53x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition | MiniMax-M2.53x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition | MiniMax-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) | – | – | – | – |
3× AMD Radeon AI PRO R9700 · this run 6 tok/s3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 116 tok/s3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 116 tok/s3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 116 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.