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

gpt-oss-120b

Performance benchmark · measured on 27.07.2026 14:38

Benchmark-IDrun-20260727-145956-fb4fba
Timebench 3 - Kombi (Prefill + Generation)MoE120BRuntime: llama.cppQuantisierung: Q4_K_M
Generation60,05tok/s
Prefill224,11tok/s
Time to First Token126.906,00ms
Total duration600,00s
Concurrency10parallel
Ranking in the field
103of 142 systems

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

This run is better than 28 % of all comparable systems.
Generation 60,1 tok/s
-85 % vs Ø 398,5
Prefill 224,1 tok/s
-97 % vs Ø 7.618,1
Time to First Token 126.906 ms
+254 % vs Ø 35.801
Distribution in the field0 – 2.414 tok/s
Ø 399 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: NVIDIA GeForce RTX 5070 Ti · 16 GB VRAM
CPU: AMD Ryzen Threadripper PRO 5975WX 32-Cores
RAM: 247 GB
Mainboard: ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI

Setup

Runtime: llama.cpp
Quantization: Q4_K_M
Model: gpt-oss-120b

Configuration

benchmark-konfiguration — run-20260727-145956-fb4fba
# LLM-Benchmark Konfiguration # Modell : gpt-oss-120b # Engine : llama.cpp # Run-ID : run-20260727-145956-fb4fba # GPU : NVIDIA GeForce RTX 5070 Ti # CPU : AMD Ryzen Threadripper PRO 5975WX 32-Cores # RAM : 247 GB bench@llm-benchmark:~$ /home/godcore/llama.cpp/build/bin/llama-server \ -m /home/godcore/.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 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.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./home/godcore/.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.0
Kontext?Groesse des Kontextfensters in Token. 0 = der beim Training verwendete Kontext des Modells.16384
np4

All benchmarks of this model To leaderboard

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

31323515678,20,001.2162.4313.647Prefill (tok/s)Generation (tok/s)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 5090 - 13,3 tok/s Generation, 369 tok/s Prefill, TTFT 16.219 ms (2 Laufe)NVIDIA GeForce RTX 50...CPU-only - 5,3 tok/s Generation, 42 tok/s Prefill, TTFT 165.568 ms (3 Laufe)CPU-onlyNVIDIA GeForce RTX 5070 Ti - 60,1 tok/s Generation, 195 tok/s Prefill, TTFT 69.936 ms (3 Laufe) | DIESER LAUF★ NVIDIA GeForce RTX 50...
AMD Radeon AI PRO R9700 241,4 tok/s★ NVIDIA GeForce RTX 5070 Ti 60,1 tok/s this runNVIDIA GeForce RTX 5090 13,3 tok/sCPU-only 5,3 tok/s

CPUby processor

31323515678,20,001.2162.4313.647Prefill (tok/s)Generation (tok/s)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 7 5800X3D 8-Core Processor - 13,3 tok/s Generation, 369 tok/s Prefill, TTFT 16.219 ms (2 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 Threadripper PRO 5975WX 32-Cores - 60,1 tok/s Generation, 195 tok/s Prefill, TTFT 69.936 ms (3 Laufe) | DIESER LAUF★ AMD Ryzen Threadrippe...
AMD Ryzen Threadripper PRO 7955WX 16-Cores 241,4 tok/s★ AMD Ryzen Threadripper PRO 5975WX 32-Cores 60,1 tok/s this runAMD Ryzen 7 5800X3D 8-Core Processor 13,3 tok/sIntel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz 5,3 tok/s

MBby mainboard

31323515678,20,001.2162.4313.647Prefill (tok/s)Generation (tok/s)ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE - 241,4 tok/s Generation, 2.947 tok/s Prefill, TTFT 5.020 ms (2 Laufe)ASUSTeK COMPUTER INC....ASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING - 13,3 tok/s Generation, 369 tok/s Prefill, TTFT 16.219 ms (2 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...ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI - 60,1 tok/s Generation, 195 tok/s Prefill, TTFT 69.936 ms (3 Laufe) | DIESER LAUF★ ASUSTeK COMPUTER INC....
ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE 241,4 tok/s★ ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI 60,1 tok/s this runASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING 13,3 tok/sDell Inc. PowerEdge R820 5,3 tok/s

ENGby engine

31123315677,80,0237477717957Prefill (tok/s)Generation (tok/s)vLLM - 13,3 tok/s Generation, 369 tok/s Prefill, TTFT 16.219 ms (2 Laufe)vLLMllama.cpp - 241,4 tok/s Generation, 826 tok/s Prefill, TTFT 89.569 ms (8 Laufe) | DIESER LAUF★ llama.cpp
★ llama.cpp 241,4 tok/s this runvLLM 13,3 tok/s

DRVby driver

266253241229217690720749778Prefill (tok/s)Generation (tok/s)unbekannt - 241,4 tok/s Generation, 734 tok/s Prefill, TTFT 74.899 ms (10 Laufe)unbekannt
unbekannt 241,4 tok/s
💰 Economics

Economics of this run

Operating cost, TCO and comparison with the next-best runs of the same model at identical concurrency (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 10 W
⚡ TDP 10 W
☁️ External LLM (API)
Electricity0.30 EUR/kWh
Avg power (incl. idle)10 W missingBoard 10 W full load
Avg cost / hourEUR 0.0030
Electricity / 1M tokensEUR 0.014
Token / kWh21.62M
Acquisition (system)EUR 2,096 missingRAM EUR 1,976 · PSU EUR 120
Electricity (2 years)
TCO (2 years)EUR 2,149
Output tokens (2 years)3.79B
☁️ External LLM (API) – comparison
External LLM cost (2 years)
Savings vs. external (2 years)
No power draw measured – values estimated from GPU TDP + CPU (idle + 15 %) + board.

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 (10 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 5070 Tigpt-oss-120b3x AMD Radeon AI PRO R9700gpt-oss-120bKeine 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.