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

MiniMax-M2.7

Performance benchmark · measured on 30.07.2026 10:28

Benchmark-IDrun-20260730-120419-2ad3a7
Timebench 3 - Kombi (Prefill + Generation)MoE230BRuntime: llama.cppQuantisierung: UD-Q4_K_M
Generation3,95tok/s
Prefill9,50tok/s
Time to First Token246.179,50ms
Total duration1.012,22s
Concurrency1parallel
Ranking in the field
55of 63 systems

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

This run is better than 13 % of all comparable systems.
Generation 4,0 tok/s
-96 % vs Ø 103,6
Prefill 9,5 tok/s
-100 % vs Ø 2.738,7
Time to First Token 246.180 ms
+599 % vs Ø 35.198
Distribution in the field1 – 246 tok/s
Ø 104 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: NVIDIA GeForce RTX 3090 Ti · 24 GB VRAM
CPU: AMD Ryzen 9 8945HX with Radeon Graphics
RAM: 92 GB
Mainboard: Meigao Innovation Technology (Shen Zhen) Co., Ltd DRFXL (MotherBoard Series)

Setup

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

Configuration

benchmark-konfiguration — run-20260730-120419-2ad3a7
# LLM-Benchmark Konfiguration # Modell : MiniMax-M2.7 # Engine : llama.cpp # Run-ID : run-20260730-120419-2ad3a7 # GPU : NVIDIA GeForce RTX 3090 Ti # CPU : AMD Ryzen 9 8945HX with Radeon Graphics # RAM : 92 GB bench@llm-benchmark:~$ /root/llama.cpp/build/bin/llama-server \ -m /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 \ --alias MiniMax-M2.7 \ --host 0.0.0.0 \ --port 8000 \ -ngl 0 \ -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-M2.7
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./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.0
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-M2.7 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

22616911356,50,001.7913.5825.373Prefill (tok/s)Generation (tok/s)NVIDIA GB10 (DGX Spark) - 174,2 tok/s Generation, 4.335 tok/s Prefill, TTFT 20.488 ms (3 Laufe)NVIDIA GB10 (DGX Spar...AMD Radeon AI PRO R9700 - 16,9 tok/s Generation, 471 tok/s Prefill, TTFT 37.428 ms (5 Laufe)AMD Radeon AI PRO R97...CPU-only - 2,6 tok/s Generation, 24 tok/s Prefill, TTFT 193.311 ms (3 Laufe)CPU-onlyNVIDIA GeForce RTX 3090 Ti - 4,0 tok/s Generation, 10 tok/s Prefill, TTFT 346.143 ms (3 Laufe) | DIESER LAUF★ NVIDIA GeForce RTX 30...
NVIDIA GB10 (DGX Spark) 174,2 tok/sAMD Radeon AI PRO R9700 16,9 tok/s★ NVIDIA GeForce RTX 3090 Ti 4,0 tok/s this runCPU-only 2,6 tok/s

CPUby processor

22616911356,50,001.7913.5825.373Prefill (tok/s)Generation (tok/s)NVIDIA Grace - 174,2 tok/s Generation, 4.335 tok/s Prefill, TTFT 20.488 ms (3 Laufe)NVIDIA GraceAMD Ryzen Threadripper PRO 7955WX 16-Cores - 16,9 tok/s Generation, 471 tok/s Prefill, TTFT 37.428 ms (5 Laufe)AMD Ryzen Threadrippe...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)Intel(R) Xeon(R) CPU ...AMD Ryzen 9 8945HX with Radeon Graphics - 4,0 tok/s Generation, 10 tok/s Prefill, TTFT 346.143 ms (3 Laufe) | DIESER LAUF★ AMD Ryzen 9 8945HX wi...
NVIDIA Grace 174,2 tok/sAMD Ryzen Threadripper PRO 7955WX 16-Cores 16,9 tok/s★ AMD Ryzen 9 8945HX with Radeon Graphics 4,0 tok/s this runIntel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz 2,6 tok/s

MBby mainboard

22616911356,50,001.7913.5825.373Prefill (tok/s)Generation (tok/s)ASUSTeK COMPUTER INC. GX10 - 174,2 tok/s Generation, 4.335 tok/s Prefill, TTFT 20.488 ms (3 Laufe)ASUSTeK COMPUTER INC....ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE - 16,9 tok/s Generation, 471 tok/s Prefill, TTFT 37.428 ms (5 Laufe)ASUSTeK COMPUTER INC....Dell Inc. PowerEdge R820 - 2,6 tok/s Generation, 24 tok/s Prefill, TTFT 193.311 ms (3 Laufe)Dell Inc. PowerEdge R...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) | DIESER LAUF★ Meigao Innovation Tec...
ASUSTeK COMPUTER INC. GX10 174,2 tok/sASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE 16,9 tok/s★ Meigao Innovation Technology (Shen Zhen) Co., Ltd DRFXL (MotherBoard Series) 4,0 tok/s this runDell Inc. PowerEdge R820 2,6 tok/s

ENGby engine

22316711255,80,009981.9972.995Prefill (tok/s)Generation (tok/s)vLLM - 174,2 tok/s Generation, 2.431 tok/s Prefill, TTFT 21.499 ms (6 Laufe)vLLMllama.cpp - 16,9 tok/s Generation, 109 tok/s Prefill, TTFT 217.247 ms (8 Laufe) | DIESER LAUF★ llama.cpp
vLLM 174,2 tok/s★ llama.cpp 16,9 tok/s this run

DRVby driver

22316711255,80,001.7783.5575.335Prefill (tok/s)Generation (tok/s)NVIDIA 590.48.01 / CUDA 13.1 - 174,2 tok/s Generation, 4.335 tok/s Prefill, TTFT 20.488 ms (3 Laufe)NVIDIA 590.48.01 / CU...unbekannt - 16,9 tok/s Generation, 223 tok/s Prefill, TTFT 164.136 ms (11 Laufe)unbekannt
NVIDIA 590.48.01 / CUDA 13.1 174,2 tok/sunbekannt 16,9 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 50 W
⚡ TDP 477 W
☁️ External LLM (API)
Electricity0.30 EUR/kWh
Avg power (incl. idle)477 W estimated (TDP)GPU 450 + CPU 17 + Board 10 W full load
Avg cost / hourEUR 0.14
Electricity / 1M tokensEUR 10.07
Token / kWh29.80K
Acquisition (system)EUR 2,986 partial priceGPU EUR 999 · CPU EUR 549 · RAM EUR 1,288 · PSU EUR 150
Electricity (2 years)
TCO (2 years)EUR 5,494
Output tokens (2 years)249.13M
☁️ 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 (50 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-M2.7NVIDIA GeForce RTX 3090 TiMiniMax-M2.7NVIDIA GB10 (DGX Spark)MiniMax-M2.7AMD Radeon AI PRO R9700MiniMax-M2.7Keine GPU (CPU-only)
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.