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

gpt-oss-120b

Performance benchmark · measured on 23.07.2026 15:17

Benchmark-IDrun-20260723-174503-884705
Timebench 3 - Kombi (Prefill + Generation)MoE120BRuntime: vLLM
For context: Teile des Modells wurden per --cpu-offload-gb=44 GB in den System-RAM ausgelagert – RAM wird als erweiterter VRAM genutzt, was den Durchsatz senken kann.
Generation6,46tok/s
Prefill332,98tok/s
Time to First Token6.063,50ms
Total duration329,29s
Concurrency1parallel
Ranking in the field
1337of 1549 systems

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

This run is better than 13 % of all comparable systems.
Generation 6,5 tok/s
-92 % vs Ø 79,0
Prefill 333,0 tok/s
-88 % vs Ø 2.837,1
Time to First Token 6.064 ms
-78 % vs Ø 26.963
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: NVIDIA GeForce RTX 5090 · 32 GB VRAM
CPU: AMD Ryzen 7 5800X3D 8-Core Processor
RAM: 126 GB
Mainboard: ASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING

Setup

Runtime: vLLM
Quantization: -
Model: gpt-oss-120b

Configuration

benchmark-konfiguration — run-20260723-174503-884705
# LLM-Benchmark Konfiguration # Modell : gpt-oss-120b # Engine : vLLM # Run-ID : run-20260723-174503-884705 # GPU : NVIDIA GeForce RTX 5090 # CPU : AMD Ryzen 7 5800X3D 8-Core Processor # RAM : 126 GB bench@llm-benchmark:~$ /opt/gcs_venv/bin/python3 /opt/gcs_venv/bin/vllm serve openai/gpt-oss-120b \ --served-model-name gpt-oss-120b \ --dtype auto \ --max-model-len 8192 \ --gpu-memory-utilization 0.92 \ --cpu-offload-gb 44 \ --trust-remote-code \ --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.vllm
Modellalias?Der Name, unter dem das Modell ueber die API angesprochen wird. Genau dieser Wert muss im Request-Feld 'model' stehen.gpt-oss-120b
Kontextlaenge?Maximale Anzahl Tokens (Eingabe + erzeugte Ausgabe zusammen), die das Modell pro Anfrage verarbeiten kann.8192
Alias?Anzeigename des Modells nach aussen (served model name), unabhaengig vom Dateinamen.gpt-oss-120b
Dtype?Zahlenformat der Modellgewichte bei der Berechnung (z.B. auto, float16, bfloat16). 'auto' waehlt automatisch das vom Modell empfohlene Format.auto
Kontext?Groesse des Kontextfensters in Token. 0 = der beim Training verwendete Kontext des Modells.8192
GPU-Speicher?Anteil des GPU-Speichers (0 bis 1), den vLLM belegen darf. 0.92 = 92 %. Hoeher = mehr Platz fuer den KV-Cache (mehr/laengere parallele Anfragen), aber groesseres Risiko fuer 'Out of Memory'.0.92
cpu-offload-gb?Menge an Modellgewichten in GiB, die in den CPU-RAM ausgelagert wird. Ermoeglicht groessere Modelle als der GPU-Speicher fasst, kostet aber Geschwindigkeit.44
Trust-Remote-Code?Erlaubt vLLM, mit dem Modell mitgelieferten Python-Code auszufuehren. Noetig fuer Architekturen, die vLLM nicht von Haus aus kennt. Nur bei vertrauenswuerdigen Modellen aktivieren.aktiv

All benchmarks of this model To leaderboard

Anzeige
Model comparison

gpt-oss-120b 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

1.7361.3028684340,002.6035.2067.808Prefill (tok/s)Generation (tok/s)NVIDIA RTX PRO 6000 Blackwell Workstation Edition - 1.335,9 tok/s Generation, 5.805 tok/s Prefill, TTFT 4.872 ms (5 Laufe)NVIDIA RTX PRO 6000 B...NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition - 1.229,7 tok/s Generation, 6.303 tok/s Prefill, TTFT 4.302 ms (12 Laufe)NVIDIA RTX PRO 6000 B...AMD Radeon PRO W7900 Dual Slot - 216,2 tok/s Generation, 1.083 tok/s Prefill, TTFT 9.148 ms (3 Laufe)AMD Radeon PRO W7900 ...AMD Radeon AI PRO R9700 - 107,0 tok/s Generation, 1.057 tok/s Prefill, TTFT 67.151 ms (13 Laufe)AMD Radeon AI PRO R97...NVIDIA GeForce RTX 3090 Ti - 85,3 tok/s Generation, 238 tok/s Prefill, TTFT 79.784 ms (3 Laufe)NVIDIA GeForce RTX 30...NVIDIA GeForce RTX 5070 Ti - 60,1 tok/s Generation, 195 tok/s Prefill, TTFT 69.936 ms (3 Laufe)NVIDIA GeForce RTX 50...Intel Arc Pro B70 - 32,4 tok/s Generation, 47 tok/s Prefill, TTFT 184.310 ms (3 Laufe)Intel Arc Pro B70NVIDIA GeForce RTX 2060 - 5,3 tok/s Generation, 42 tok/s Prefill, TTFT 165.568 ms (3 Laufe)NVIDIA GeForce RTX 20...NVIDIA GeForce RTX 5090 - 42,3 tok/s Generation, 239 tok/s Prefill, TTFT 76.971 ms (5 Laufe) | DIESER LAUF★ NVIDIA GeForce RTX 50...
NVIDIA RTX PRO 6000 Blackwell Workstation Edition 1.335,9 tok/sNVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 1.229,7 tok/sAMD Radeon PRO W7900 Dual Slot 216,2 tok/sAMD Radeon AI PRO R9700 107,0 tok/sNVIDIA GeForce RTX 3090 Ti 85,3 tok/sNVIDIA GeForce RTX 5070 Ti 60,1 tok/s★ NVIDIA GeForce RTX 5090 42,3 tok/s this runIntel Arc Pro B70 32,4 tok/sNVIDIA GeForce RTX 2060 5,3 tok/s

CPUby processor

1.7361.3028684340,002.6035.2067.808Prefill (tok/s)Generation (tok/s)AMD Ryzen 9 9950X 16-Core Processor - 1.335,9 tok/s Generation, 5.805 tok/s Prefill, TTFT 4.872 ms (5 Laufe)AMD Ryzen 9 9950X 16-...AMD Ryzen Threadripper PRO 9965WX 24-Cores - 1.229,7 tok/s Generation, 6.303 tok/s Prefill, TTFT 4.302 ms (12 Laufe)AMD Ryzen Threadrippe...AMD Ryzen Threadripper PRO 5975WX 32-Cores - 216,2 tok/s Generation, 639 tok/s Prefill, TTFT 39.542 ms (6 Laufe)AMD Ryzen Threadrippe...AMD Ryzen Threadripper PRO 7955WX 16-Cores - 107,0 tok/s Generation, 1.057 tok/s Prefill, TTFT 67.151 ms (13 Laufe)AMD Ryzen Threadrippe...AMD Ryzen 9 8945HX with Radeon Graphics - 85,3 tok/s Generation, 238 tok/s Prefill, TTFT 79.784 ms (3 Laufe)AMD Ryzen 9 8945HX wi...AMD Ryzen 9 7945HX with Radeon Graphics - 32,4 tok/s Generation, 47 tok/s Prefill, TTFT 184.310 ms (3 Laufe)AMD Ryzen 9 7945HX wi...Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz - 5,3 tok/s Generation, 42 tok/s Prefill, TTFT 165.568 ms (3 Laufe)Intel(R) Xeon(R) CPU ...AMD Ryzen 7 5800X3D 8-Core Processor - 42,3 tok/s Generation, 239 tok/s Prefill, TTFT 76.971 ms (5 Laufe) | DIESER LAUF★ AMD Ryzen 7 5800X3D 8...
AMD Ryzen 9 9950X 16-Core Processor 1.335,9 tok/sAMD Ryzen Threadripper PRO 9965WX 24-Cores 1.229,7 tok/sAMD Ryzen Threadripper PRO 5975WX 32-Cores 216,2 tok/sAMD Ryzen Threadripper PRO 7955WX 16-Cores 107,0 tok/sAMD Ryzen 9 8945HX with Radeon Graphics 85,3 tok/s★ AMD Ryzen 7 5800X3D 8-Core Processor 42,3 tok/s this runAMD Ryzen 9 7945HX with Radeon Graphics 32,4 tok/sIntel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz 5,3 tok/s

MBby mainboard

1.7361.3028684340,002.3974.7937.190Prefill (tok/s)Generation (tok/s)ASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI - 1.335,9 tok/s Generation, 5.805 tok/s Prefill, TTFT 4.872 ms (5 Laufe)ASUSTeK COMPUTER INC....ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE - 1.229,7 tok/s Generation, 3.575 tok/s Prefill, TTFT 36.983 ms (25 Laufe)ASUSTeK COMPUTER INC....ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI - 216,2 tok/s Generation, 639 tok/s Prefill, TTFT 39.542 ms (6 Laufe)ASUSTeK COMPUTER INC....Meigao Innovation Technology (Shen Zhen) Co., Ltd DRFXL (MotherBoard Series) - 85,3 tok/s Generation, 238 tok/s Prefill, TTFT 79.784 ms (3 Laufe)Meigao Innovation Tec...Shenzhen Meigao Electronic Equipment Co.,Ltd DRFXI (MotherBoard Series) - 32,4 tok/s Generation, 47 tok/s Prefill, TTFT 184.310 ms (3 Laufe)Shenzhen Meigao Elect...Dell Inc. PowerEdge R820 - 5,3 tok/s Generation, 42 tok/s Prefill, TTFT 165.568 ms (3 Laufe)Dell Inc. PowerEdge R...ASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING - 42,3 tok/s Generation, 239 tok/s Prefill, TTFT 76.971 ms (5 Laufe) | DIESER LAUF★ ASUSTeK COMPUTER INC....
ASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI 1.335,9 tok/sASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE 1.229,7 tok/sASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI 216,2 tok/sMeigao Innovation Technology (Shen Zhen) Co., Ltd DRFXL (MotherBoard Series) 85,3 tok/s★ ASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING 42,3 tok/s this runShenzhen Meigao Electronic Equipment Co.,Ltd DRFXI (MotherBoard Series) 32,4 tok/sDell Inc. PowerEdge R820 5,3 tok/s

ENGby engine

1.7321.2998664330,01.2352.0082.7813.554Prefill (tok/s)Generation (tok/s)llama.cpp - 1.335,9 tok/s Generation, 2.514 tok/s Prefill, TTFT 62.788 ms (45 Laufe)llama.cppunbekannt - 99,8 tok/s Generation, 3.110 tok/s Prefill, TTFT 789 ms (2 Laufe)unbekanntvLLM - 21,5 tok/s Generation, 1.679 tok/s Prefill, TTFT 10.998 ms (3 Laufe) | DIESER LAUF★ vLLM
llama.cpp 1.335,9 tok/sunbekannt 99,8 tok/s★ vLLM 21,5 tok/s this run

DRVby driver

1.7301.2988654330,001.2832.5653.848Prefill (tok/s)Generation (tok/s)unbekannt - 1.335,9 tok/s Generation, 2.623 tok/s Prefill, TTFT 51.234 ms (45 Laufe)unbekanntAMD 7.0.0-27-generic - 99,8 tok/s Generation, 3.110 tok/s Prefill, TTFT 789 ms (2 Laufe)AMD 7.0.0-27-genericIntel 26.18.38308.4 - 32,4 tok/s Generation, 47 tok/s Prefill, TTFT 184.310 ms (3 Laufe)Intel 26.18.38308.4
unbekannt 1.335,9 tok/sAMD 7.0.0-27-generic 99,8 tok/sIntel 26.18.38308.4 32,4 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 72 W
⚡ TDP 622 W
☁️ External LLM (API)
Electricity0.30 EUR/kWh
Avg power (incl. idle)622 W estimated (TDP)GPU 575 + CPU 35 + Board 12 W full load
Avg cost / hourEUR 0.19
Electricity / 1M tokensEUR 8.02
Token / kWh37.42K
Acquisition (system)EUR 4,986 full priceGPU EUR 3,300 · CPU EUR 349 · Board EUR 149 · RAM EUR 1,008 · PSU EUR 180
Electricity (2 years)
TCO (2 years)EUR 8,253
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 (72 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

gpt-oss-120bNVIDIA GeForce RTX 5090gpt-oss-120bNVIDIA RTX PRO 6000 Blackwell Workstation Editiongpt-oss-120b3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Editiongpt-oss-120b3x 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.