ℹ

For context: Diese Plattform nutzt Unified Memory – die "VRAM" ist gemeinsamer System-RAM (APU/Superchip); das Modell teilt sich den Speicher mit dem System.

Generation0,02tok/s

Prefill4,86tok/s

Time to First Token485.856,00ms

Total duration1.200,00s

Concurrency1parallel

Ranking in the field

This GPU All GPUs

470of 470 systems

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

This run is better than 0 % of all comparable systems.

Generation 0,0 tok/s

-100 % vs Ø 124,8

Prefill 4,9 tok/s

-100 % vs Ø 3.292,9

Time to First Token 485.856 ms

+4.261 % vs Ø 11.142

Distribution in the field0 – 405 tok/s

Ø 125 Median Dieser Lauf

Wie schlägt sich dieser Benchmark mit anderen Modellen?

gpt-oss-20bNVIDIA GeForce RTX 5090 · run-20260724-004608-16af9b

404,6 tok/s

gpt-oss-20bNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260730-035052-9f766a

395,2 tok/s

NVIDIA-Nemotron-3-Nano-4BNVIDIA GeForce RTX 5090 · run-20260728-194135-d456e7

393,5 tok/s

NVIDIA-Nemotron-3-Nano-4BNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260727-181607-bffb11

393,5 tok/s

gpt-oss-20bNVIDIA GeForce RTX 5090 · run-20260724-004607-29bd16

388,9 tok/s

gpt-oss-20bNVIDIA GeForce RTX 5090 · run-20260729-032121-1c779f

388,2 tok/s

gemma-4-E2B-itNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260727-181606-6ea089

378,6 tok/s

gemma-4-E2B-itNVIDIA GeForce RTX 5090 · run-20260728-184455-e8b129

377,6 tok/s

NVIDIA-Nemotron-3-Nano-4B3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-194136-ac388e

362,3 tok/s

NVIDIA-Nemotron-3-Nano-4B3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-194136-5e5085

361,4 tok/s

NVIDIA-Nemotron-3-Nano-30B-A3BNVIDIA GeForce RTX 5090 · run-20260729-105335-653788

359,4 tok/s

Nemotron-3-Nano-Omni-30B-A3B-ReasoningNVIDIA GeForce RTX 5090 · run-20260729-105334-2c4905

359,3 tok/s

Nemotron-Cascade-2-30B-A3BNVIDIA GeForce RTX 5090 · run-20260729-105334-44d1e7

359,0 tok/s

Nemotron-3-Nano-Omni-30B-A3B-ReasoningNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260729-032119-4852bf

357,1 tok/s

command-a-reasoning-08-2025 this runIntel Arc Pro B70 · run-20260730-035053-91934d

0,0 tok/s

How does this benchmark compare on other GPUs?

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

NVIDIA RTX PRO 6000 Blackwell Workstation Editionrun-20260727-193100-bb2f69

21,9 tok/s

3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Editionrun-20260727-181606-39296d

21,1 tok/s

3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Editionrun-20260730-035053-24f0d3

20,8 tok/s

3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Editionrun-20260730-035053-40cb2f

20,7 tok/s

3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Editionrun-20260730-035052-9ec58a

17,7 tok/s

NVIDIA GeForce RTX 5070 Tirun-20260727-113142-daa7d7

2,2 tok/s

NVIDIA GeForce RTX 3090 Tirun-20260727-145956-e200a6

1,4 tok/s

NVIDIA GeForce RTX 5090run-20260728-195914-895e29

0,7 tok/s

Intel Arc Pro B70 this runrun-20260730-035053-91934d

0,0 tok/s

Hardware

GPU: Intel Arc Pro B70 · 32 GB VRAM
CPU: AMD Ryzen 9 7945HX with Radeon Graphics
RAM: 29 GB
Mainboard: Shenzhen Meigao Electronic Equipment Co.,Ltd DRFXI (MotherBoard Series)

Setup

Runtime: llama.cpp
Quantization: Q4_K_M
Model: command-a-reasoning-08-2025

Configuration

benchmark-konfiguration — run-20260730-035053-91934d

# LLM-Benchmark Konfiguration # Modell : command-a-reasoning-08-2025 # Engine : llama.cpp # Run-ID : run-20260730-035053-91934d # GPU : Intel Arc Pro B70 # CPU : AMD Ryzen 9 7945HX with Radeon Graphics # RAM : 29 GB bench@llm-benchmark:~$ /root/llama.cpp/build/bin/llama-server \ -m /root/.cache/huggingface/hub/models--DevQuasar--CohereLabs.command-a-reasoning-08-2025-GGUF/snapshots/924408415a0e807b935d0a0c4f316a1bc40a1051/CohereLabs.command-a-reasoning-08-2025.Q4_K_M-00001-of-00005.gguf \ --alias command-a-reasoning-08-2025 \ --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.	command-a-reasoning-08-2025
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--DevQuasar--CohereLabs.command-a-reasoning-08-2025-GGUF/snapshots/924408415a0e807b935d0a0c4f316a1bc40a1051/CohereLabs.command-a-reasoning-08-2025.Q4_K_M-00001-of-00005.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
np	4

All benchmarks of this model To leaderboard

Model comparison

command-a-reasoning-08-2025 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 Workstation Edition 157,0 tok/sNVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 134,9 tok/sNVIDIA GeForce RTX 5070 Ti 6,7 tok/sNVIDIA GeForce RTX 3090 Ti 4,2 tok/sNVIDIA GeForce RTX 5090 2,2 tok/s★ Intel Arc Pro B70 0,0 tok/s this run

CPUby processor

AMD Ryzen 9 9950X 16-Core Processor 157,0 tok/sAMD Ryzen Threadripper PRO 9965WX 24-Cores 134,9 tok/sAMD Ryzen Threadripper PRO 5975WX 32-Cores 6,7 tok/sAMD Ryzen 9 8945HX with Radeon Graphics 4,2 tok/sAMD Ryzen 7 5800X3D 8-Core Processor 2,2 tok/s★ AMD Ryzen 9 7945HX with Radeon Graphics 0,0 tok/s this run

MBby mainboard

ASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI 157,0 tok/sASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE 134,9 tok/sASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI 6,7 tok/sMeigao Innovation Technology (Shen Zhen) Co., Ltd DRFXL (MotherBoard Series) 4,2 tok/sASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING 2,2 tok/s★ Shenzhen Meigao Electronic Equipment Co.,Ltd DRFXI (MotherBoard Series) 0,0 tok/s this run

ENGby engine

★ llama.cpp 157,0 tok/s this run

DRVby driver

unbekannt 157,0 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 URL Reset

⚡ Electricity price EUR/kWh

⚙️ System utilization 100 %

🖥️ Acquisition EUR

🔌 Idle 0 W

⚡ TDP 230 W

☁️ External LLM (API) show

Input €/1M Output €/1M Input per output token

Electricity0.30 EUR/kWh

Avg power (incl. idle)230 W estimated (TDP)GPU 230 W full load

Avg cost / hourEUR 0.069

Electricity / 1M tokensEUR 958.33

Token / kWh313

Acquisition (system)EUR 120 missingPSU EUR 120

Electricity (2 years)–

TCO (2 years)EUR 1,329

Output tokens (2 years)1.26M

☁️ 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 (0 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

	command-a-reasoning-08-2025Intel Arc Pro B70	command-a-reasoning-08-2025NVIDIA RTX PRO 6000 Blackwell Workstation Edition	command-a-reasoning-08-20253x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition	command-a-reasoning-08-20253x 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)	–	–	–	–

Intel Arc Pro B70 · this run 0 tok/s NVIDIA RTX PRO 6000 Blackwell Workstation Edition 22 tok/s 3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 21 tok/s 3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 21 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.