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

gpt-oss-120b

Performance benchmark · measured on 30.07.2026 03:27

Benchmark-IDrun-20260730-035055-422523
Timebench 3 - Kombi (Prefill + Generation)MoE120BRuntime: llama.cppQuantisierung: Q4_K_M
For context: Diese Plattform nutzt Unified Memory – die "VRAM" ist gemeinsamer System-RAM (APU/Superchip); das Modell teilt sich den Speicher mit dem System.
Generation26,57tok/s
Prefill50,22tok/s
Time to First Token276.963,50ms
Total duration1.200,00s
Concurrency10parallel
Ranking in the field
3of 3 systems

Performance benchmark · Primary metric: Generation-Speed (tok/s) · 10× concurrent

This run is better than 0 % of all comparable systems.
Generation 26,6 tok/s
-94 % vs Ø 442,5
Prefill 50,2 tok/s
-97 % vs Ø 1.679,9
Time to First Token 276.964 ms
+161 % vs Ø 106.242
Distribution in the field27 – 826 tok/s
Ø 443 Median Dieser Lauf

Wie schlägt sich dieser Benchmark mit anderen Modellen?

How does this benchmark compare on other GPUs?

Same model on different hardware · 10× concurrent · Generation (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: gpt-oss-120b

Configuration

benchmark-konfiguration — run-20260730-035055-422523
# LLM-Benchmark Konfiguration # Modell : gpt-oss-120b # Engine : llama.cpp # Run-ID : run-20260730-035055-422523 # 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--unsloth--gpt-oss-120b-GGUF/snapshots/ff1a82da6ad466e32284fa3d2b86694db3204789/Q4_K_M/gpt-oss-120b-Q4_K_M-00001-of-00002.gguf \ --alias gpt-oss-120b \ --host 0.0.0.0 \ --port 8000 \ -ngl 12 \ -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.gpt-oss-120b
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--gpt-oss-120b-GGUF/snapshots/ff1a82da6ad466e32284fa3d2b86694db3204789/Q4_K_M/gpt-oss-120b-Q4_K_M-00001-of-00002.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.12
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

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 AI PRO R9700 - 241,4 tok/s Generation, 2.947 tok/s Prefill, TTFT 5.020 ms (2 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...NVIDIA GeForce RTX 5090 - 42,3 tok/s Generation, 239 tok/s Prefill, TTFT 76.971 ms (5 Laufe)NVIDIA GeForce RTX 50...CPU-only - 5,3 tok/s Generation, 42 tok/s Prefill, TTFT 165.568 ms (3 Laufe)CPU-onlyIntel Arc Pro B70 - 32,4 tok/s Generation, 47 tok/s Prefill, TTFT 184.310 ms (3 Laufe) | DIESER LAUF★ Intel Arc Pro B70
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 AI PRO R9700 241,4 tok/sNVIDIA GeForce RTX 3090 Ti 85,3 tok/sNVIDIA GeForce RTX 5070 Ti 60,1 tok/sNVIDIA GeForce RTX 5090 42,3 tok/s★ Intel Arc Pro B70 32,4 tok/s this runCPU-only 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 7955WX 16-Cores - 241,4 tok/s Generation, 2.947 tok/s Prefill, TTFT 5.020 ms (2 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 Threadripper PRO 5975WX 32-Cores - 60,1 tok/s Generation, 195 tok/s Prefill, TTFT 69.936 ms (3 Laufe)AMD Ryzen Threadrippe...AMD Ryzen 7 5800X3D 8-Core Processor - 42,3 tok/s Generation, 239 tok/s Prefill, TTFT 76.971 ms (5 Laufe)AMD Ryzen 7 5800X3D 8...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 9 7945HX with Radeon Graphics - 32,4 tok/s Generation, 47 tok/s Prefill, TTFT 184.310 ms (3 Laufe) | DIESER LAUF★ AMD Ryzen 9 7945HX wi...
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 7955WX 16-Cores 241,4 tok/sAMD Ryzen 9 8945HX with Radeon Graphics 85,3 tok/sAMD Ryzen Threadripper PRO 5975WX 32-Cores 60,1 tok/sAMD Ryzen 7 5800X3D 8-Core Processor 42,3 tok/s★ AMD Ryzen 9 7945HX with Radeon Graphics 32,4 tok/s this runIntel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz 5,3 tok/s

MBby mainboard

1.7361.3028684340,002.4054.8097.214Prefill (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, 5.824 tok/s Prefill, TTFT 4.404 ms (14 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...ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI - 60,1 tok/s Generation, 195 tok/s Prefill, TTFT 69.936 ms (3 Laufe)ASUSTeK COMPUTER INC....ASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING - 42,3 tok/s Generation, 239 tok/s Prefill, TTFT 76.971 ms (5 Laufe)ASUSTeK COMPUTER INC....Dell Inc. PowerEdge R820 - 5,3 tok/s Generation, 42 tok/s Prefill, TTFT 165.568 ms (3 Laufe)Dell Inc. PowerEdge R...Shenzhen Meigao Electronic Equipment Co.,Ltd DRFXI (MotherBoard Series) - 32,4 tok/s Generation, 47 tok/s Prefill, TTFT 184.310 ms (3 Laufe) | DIESER LAUF★ Shenzhen Meigao Elect...
ASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI 1.335,9 tok/sASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE 1.229,7 tok/sMeigao Innovation Technology (Shen Zhen) Co., Ltd DRFXL (MotherBoard Series) 85,3 tok/sASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI 60,1 tok/sASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING 42,3 tok/s★ Shenzhen Meigao Electronic Equipment Co.,Ltd DRFXI (MotherBoard Series) 32,4 tok/s this runDell Inc. PowerEdge R820 5,3 tok/s

ENGby engine

1.7341.3008674330,001.3462.6934.039Prefill (tok/s)Generation (tok/s)vLLM - 13,3 tok/s Generation, 369 tok/s Prefill, TTFT 16.219 ms (2 Laufe)vLLMllama.cpp - 1.335,9 tok/s Generation, 3.311 tok/s Prefill, TTFT 56.977 ms (34 Laufe) | DIESER LAUF★ llama.cpp
★ llama.cpp 1.335,9 tok/s this runvLLM 13,3 tok/s

DRVby driver

1.4691.4031.3361.2691.2022.9593.0853.2113.336Prefill (tok/s)Generation (tok/s)unbekannt - 1.335,9 tok/s Generation, 3.148 tok/s Prefill, TTFT 54.713 ms (36 Laufe)unbekannt
unbekannt 1.335,9 tok/s
💰 Economics

Economics of this run

Operating cost, TCO and comparison with the next-best runs of the same model at identical concurrency (10× 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 0 W
⚡ TDP 230 W
☁️ External LLM (API)
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 0.72
Token / kWh415.88K
Acquisition (system)EUR 120 missingPSU EUR 120
Electricity (2 years)
TCO (2 years)EUR 1,329
Output tokens (2 years)1.68B
☁️ 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

gpt-oss-120bIntel Arc Pro B70gpt-oss-120bNVIDIA RTX PRO 6000 Blackwell Workstation Editiongpt-oss-120bNVIDIA RTX PRO 6000 Blackwell 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.