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

gpt-oss-20b

Performance benchmark · measured on 21.07.2026 17:00

Benchmark-IDrun-20260722-165908-ff206d
MoE20BRuntime: godclawQuantisierung: Q4_K_M
Generation137,66tok/s
Prefill4.422,37tok/s
Time to First Token444,50ms
Total duration15,77s
Concurrency1parallel
Ranking in the field
6of 455 systems

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

This run is better than 99 % of all comparable systems.
Generation 137,7 tok/s
+290 % vs Ø 35,3
Prefill 4.422,4 tok/s
+125 % vs Ø 1.966,4
Time to First Token 445 ms
-99 % vs Ø 35.848
Distribution in the field1 – 148 tok/s
Ø 35 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: 3x AMD Radeon AI PRO R9700 · 32 GB VRAM
CPU: 32x AMD Ryzen Threadripper PRO 7955WX 16-Cores
RAM: 184 GB
Mainboard: ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE

Setup

Runtime: godclaw
Quantization: Q4_K_M
Operating system: Ubuntu 26.04 LTS (Kernel 7.0.0-27-generic)
Driver: AMD 7.0.0-27-generic
Model: gpt-oss-20b

Anmerkung

llama.cpp . 3 GPU . GGUF (unsloth/gpt-oss-20b-GGUF)

Configuration

benchmark-konfiguration — run-20260722-165908-ff206d
# LLM-Benchmark Konfiguration # Modell : gpt-oss-20b # Run-ID : run-20260722-165908-ff206d # GPU : 3x AMD Radeon AI PRO R9700 # CPU : 32x AMD Ryzen Threadripper PRO 7955WX 16-Cores # RAM : 184 GB bench@llm-benchmark:~$ cat benchmark.conf Konfigurationspfad /root/.cache/huggingface/hub/models--unsloth--gpt-oss-20b-GGUF/snapshots/d449b42d93e1c2c7bda5312f5c25c8fb91dfa9b4/gpt-oss-20b-Q4_K_M.gguf Engine llamacpp Modellalias gpt-oss-20b Kontextlaenge 8192 GPU-Layer 999 Split-Mode layer 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.llamacpp
Modellalias?Der Name, unter dem das Modell ueber die API angesprochen wird. Genau dieser Wert muss im Request-Feld 'model' stehen.gpt-oss-20b
Kontextlaenge?Maximale Anzahl Tokens (Eingabe + erzeugte Ausgabe zusammen), die das Modell pro Anfrage verarbeiten kann.8192
Modellpfad?Pfad zur GGUF-Modelldatei, die geladen und ausgeliefert wird./root/.cache/huggingface/hub/models--unsloth--gpt-oss-20b-GGUF/snapshots/d449b42d93e1c2c7bda5312f5c25c8fb91dfa9b4/gpt-oss-20b-Q4_K_M.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.999
Kontext?Groesse des Kontextfensters in Token. 0 = der beim Training verwendete Kontext des Modells.8192
Alias?Anzeigename des Modells nach aussen (served model name), unabhaengig vom Dateinamen.gpt-oss-20b
Split-Mode?Verteilung ueber mehrere GPUs: none (nur eine GPU), layer (Layer aufteilen) oder row (Tensoren zeilenweise).layer
Host?Netzwerk-Interface, an das der HTTP-Server bindet, z.B. 0.0.0.0 fuer alle Interfaces.0.0.0.0
Port?TCP-Port des HTTP-Servers.8000

All benchmarks of this model To leaderboard

Anzeige
Videoreihe und Benchmarkauswertung zur AMD R9700
Model comparison

gpt-oss-20b 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

2.5911.9431.2966480,008.07916.15724.236Prefill (tok/s)Generation (tok/s)NVIDIA RTX PRO 6000 Blackwell Workstation Edition - 1.995,4 tok/s Generation, 19.558 tok/s Prefill, TTFT 1.895 ms (8 Laufe)NVIDIA RTX PRO 6000 B...NVIDIA GeForce RTX 5090 - 1.890,7 tok/s Generation, 11.034 tok/s Prefill, TTFT 4.372 ms (18 Laufe)NVIDIA GeForce RTX 50...NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition - 1.835,7 tok/s Generation, 13.385 tok/s Prefill, TTFT 2.313 ms (15 Laufe)NVIDIA RTX PRO 6000 B...NVIDIA GeForce RTX 5070 Ti - 1.210,3 tok/s Generation, 4.544 tok/s Prefill, TTFT 11.765 ms (6 Laufe)NVIDIA GeForce RTX 50...NVIDIA GeForce RTX 3090 Ti - 1.113,5 tok/s Generation, 6.760 tok/s Prefill, TTFT 3.631 ms (22 Laufe)NVIDIA GeForce RTX 30...AMD Radeon PRO W7900 Dual Slot - 344,1 tok/s Generation, 2.818 tok/s Prefill, TTFT 3.556 ms (9 Laufe)AMD Radeon PRO W7900 ...NVIDIA GB10 (DGX Spark) - 202,1 tok/s Generation, 4.104 tok/s Prefill, TTFT 2.448 ms (3 Laufe)NVIDIA GB10 (DGX Spar...NVIDIA Tesla P100 PCIe 16GB - 111,1 tok/s Generation, 646 tok/s Prefill, TTFT 16.076 ms (3 Laufe)NVIDIA Tesla P100 PCI...AMD Radeon 8060S Graphics - 74,4 tok/s Generation, 1.168 tok/s Prefill, TTFT 12.711 ms (2 Laufe)AMD Radeon 8060S Grap...CPU-only - 14,5 tok/s Generation, 88 tok/s Prefill, TTFT 122.346 ms (3 Laufe)CPU-onlyAMD Radeon AI PRO R9700 - 163,6 tok/s Generation, 2.674 tok/s Prefill, TTFT 27.436 ms (21 Laufe) | DIESER LAUF★ AMD Radeon AI PRO R97...
NVIDIA RTX PRO 6000 Blackwell Workstation Edition 1.995,4 tok/sNVIDIA GeForce RTX 5090 1.890,7 tok/sNVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 1.835,7 tok/sNVIDIA GeForce RTX 5070 Ti 1.210,3 tok/sNVIDIA GeForce RTX 3090 Ti 1.113,5 tok/sAMD Radeon PRO W7900 Dual Slot 344,1 tok/sNVIDIA GB10 (DGX Spark) 202,1 tok/s★ AMD Radeon AI PRO R9700 163,6 tok/s this runNVIDIA Tesla P100 PCIe 16GB 111,1 tok/sAMD Radeon 8060S Graphics 74,4 tok/sCPU-only 14,5 tok/s

CPUby processor

2.5911.9431.2966480,008.07916.15724.236Prefill (tok/s)Generation (tok/s)AMD Ryzen 9 9950X 16-Core Processor - 1.995,4 tok/s Generation, 19.558 tok/s Prefill, TTFT 1.895 ms (8 Laufe)AMD Ryzen 9 9950X 16-...AMD Ryzen 7 5800X3D 8-Core Processor - 1.890,7 tok/s Generation, 11.034 tok/s Prefill, TTFT 4.372 ms (18 Laufe)AMD Ryzen 7 5800X3D 8...AMD Ryzen Threadripper PRO 9965WX 24-Cores - 1.835,7 tok/s Generation, 13.385 tok/s Prefill, TTFT 2.313 ms (15 Laufe)AMD Ryzen Threadrippe...AMD Ryzen Threadripper PRO 5975WX 32-Cores - 1.210,3 tok/s Generation, 3.508 tok/s Prefill, TTFT 6.840 ms (15 Laufe)AMD Ryzen Threadrippe...AMD Ryzen 9 8945HX with Radeon Graphics - 1.113,5 tok/s Generation, 6.303 tok/s Prefill, TTFT 4.194 ms (18 Laufe)AMD Ryzen 9 8945HX wi...AMD Ryzen 5 5600X 6-Core Processor - 572,1 tok/s Generation, 8.817 tok/s Prefill, TTFT 1.101 ms (4 Laufe)AMD Ryzen 5 5600X 6-C...NVIDIA Grace - 202,1 tok/s Generation, 4.104 tok/s Prefill, TTFT 2.448 ms (3 Laufe)NVIDIA GraceAMD Ryzen 9 7945HX with Radeon Graphics - 111,1 tok/s Generation, 646 tok/s Prefill, TTFT 16.076 ms (3 Laufe)AMD Ryzen 9 7945HX wi...AMD RYZEN AI MAX+ 395 w/ Radeon 8060S - 74,4 tok/s Generation, 1.168 tok/s Prefill, TTFT 12.711 ms (2 Laufe)AMD RYZEN AI MAX+ 395...Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz - 14,5 tok/s Generation, 88 tok/s Prefill, TTFT 122.346 ms (3 Laufe)Intel(R) Xeon(R) CPU ...AMD Ryzen Threadripper PRO 7955WX 16-Cores - 163,6 tok/s Generation, 2.674 tok/s Prefill, TTFT 27.436 ms (21 Laufe) | DIESER LAUF★ AMD Ryzen Threadrippe...
AMD Ryzen 9 9950X 16-Core Processor 1.995,4 tok/sAMD Ryzen 7 5800X3D 8-Core Processor 1.890,7 tok/sAMD Ryzen Threadripper PRO 9965WX 24-Cores 1.835,7 tok/sAMD Ryzen Threadripper PRO 5975WX 32-Cores 1.210,3 tok/sAMD Ryzen 9 8945HX with Radeon Graphics 1.113,5 tok/sAMD Ryzen 5 5600X 6-Core Processor 572,1 tok/sNVIDIA Grace 202,1 tok/s★ AMD Ryzen Threadripper PRO 7955WX 16-Cores 163,6 tok/s this runAMD Ryzen 9 7945HX with Radeon Graphics 111,1 tok/sAMD RYZEN AI MAX+ 395 w/ Radeon 8060S 74,4 tok/sIntel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz 14,5 tok/s

MBby mainboard

2.5911.9431.2966480,008.07916.15724.236Prefill (tok/s)Generation (tok/s)ASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI - 1.995,4 tok/s Generation, 19.558 tok/s Prefill, TTFT 1.895 ms (8 Laufe)ASUSTeK COMPUTER INC....ASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING - 1.890,7 tok/s Generation, 11.034 tok/s Prefill, TTFT 4.372 ms (18 Laufe)ASUSTeK COMPUTER INC....ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI - 1.210,3 tok/s Generation, 3.508 tok/s Prefill, TTFT 6.840 ms (15 Laufe)ASUSTeK COMPUTER INC....Meigao Innovation Technology (Shen Zhen) Co., Ltd DRFXL (MotherBoard Series) - 1.113,5 tok/s Generation, 6.303 tok/s Prefill, TTFT 4.194 ms (18 Laufe)Meigao Innovation Tec...ASUSTeK COMPUTER INC. PRIME A520M-K - 572,1 tok/s Generation, 8.817 tok/s Prefill, TTFT 1.101 ms (4 Laufe)ASUSTeK COMPUTER INC....ASUSTeK COMPUTER INC. GX10 - 202,1 tok/s Generation, 4.104 tok/s Prefill, TTFT 2.448 ms (3 Laufe)ASUSTeK COMPUTER INC....Shenzhen Meigao Electronic Equipment Co.,Ltd F1FXM (DeskMini Series) - 111,1 tok/s Generation, 646 tok/s Prefill, TTFT 16.076 ms (3 Laufe)Shenzhen Meigao Elect...Bosgame AXB35-02 (BeyondMax Series) - 74,4 tok/s Generation, 1.168 tok/s Prefill, TTFT 12.711 ms (2 Laufe)Bosgame AXB35-02 (Bey...Dell Inc. PowerEdge R820 - 14,5 tok/s Generation, 88 tok/s Prefill, TTFT 122.346 ms (3 Laufe)Dell Inc. PowerEdge R...ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE - 1.835,7 tok/s Generation, 7.137 tok/s Prefill, TTFT 16.968 ms (36 Laufe) | DIESER LAUF★ ASUSTeK COMPUTER INC....
ASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI 1.995,4 tok/sASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING 1.890,7 tok/s★ ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE 1.835,7 tok/s this runASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI 1.210,3 tok/sMeigao Innovation Technology (Shen Zhen) Co., Ltd DRFXL (MotherBoard Series) 1.113,5 tok/sASUSTeK COMPUTER INC. PRIME A520M-K 572,1 tok/sASUSTeK COMPUTER INC. GX10 202,1 tok/sShenzhen Meigao Electronic Equipment Co.,Ltd F1FXM (DeskMini Series) 111,1 tok/sBosgame AXB35-02 (BeyondMax Series) 74,4 tok/sDell Inc. PowerEdge R820 14,5 tok/s

ENGby engine

2.5641.9231.2826410,02.9585.7858.61211.440Prefill (tok/s)Generation (tok/s)llama.cpp - 1.995,4 tok/s Generation, 6.673 tok/s Prefill, TTFT 16.381 ms (70 Laufe)llama.cppvLLM - 1.443,9 tok/s Generation, 9.881 tok/s Prefill, TTFT 5.436 ms (34 Laufe)vLLMunbekannt - 147,8 tok/s Generation, 4.516 tok/s Prefill, TTFT 616 ms (6 Laufe)unbekannt
llama.cpp 1.995,4 tok/svLLM 1.443,9 tok/sunbekannt 147,8 tok/s

DRVby driver

2.5641.9231.2826410,02.9644.9666.9688.970Prefill (tok/s)Generation (tok/s)unbekannt - 1.995,4 tok/s Generation, 7.829 tok/s Prefill, TTFT 13.111 ms (101 Laufe)unbekanntNVIDIA 590.48.01 / CUDA 13.1 - 202,1 tok/s Generation, 4.104 tok/s Prefill, TTFT 2.448 ms (3 Laufe)NVIDIA 590.48.01 / CU...AMD 7.0.0-27-generic - 147,8 tok/s Generation, 4.516 tok/s Prefill, TTFT 616 ms (6 Laufe) | DIESER LAUF★ AMD 7.0.0-27-generic
unbekannt 1.995,4 tok/sNVIDIA 590.48.01 / CUDA 13.1 202,1 tok/s★ AMD 7.0.0-27-generic 147,8 tok/s this run
💰 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 125 W
⚡ TDP 971 W
☁️ External LLM (API)
Electricity0.30 EUR/kWh
Avg power (incl. idle)971 W estimated (TDP)GPU 900 + CPU 46 + Board 25 W full load
Avg cost / hourEUR 0.29
Electricity / 1M tokensEUR 0.59
Token / kWh510.38K
Acquisition (system)EUR 9,674 full priceGPU EUR 4,200 · CPU EUR 1,399 · Board EUR 1,299 · RAM EUR 2,576 · PSU EUR 200
Electricity (2 years)
TCO (2 years)EUR 14,778
Output tokens (2 years)8.68B
☁️ 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 (125 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-20b3x AMD Radeon AI PRO R9700gpt-oss-20bNVIDIA GeForce RTX 5090gpt-oss-20bNVIDIA RTX PRO 6000 Blackwell Workstation Editiongpt-oss-20bNVIDIA GeForce RTX 5090
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.