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

Seed-OSS-36B-Instruct

Performance benchmark · measured on 29.07.2026 09:10

Benchmark-IDrun-20260729-105338-8d4996
Timebench 3 - Kombi (Prefill + Generation)36BRuntime: llama.cppQuantisierung: Q4_K_M
Generation16,70tok/s
Prefill923,94tok/s
Time to First Token2.387,50ms
Total duration127,44s
Concurrency1parallel
Ranking in the field
340of 430 systems

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

This run is better than 21 % of all comparable systems.
Generation 16,7 tok/s
-87 % vs Ø 127,6
Prefill 923,9 tok/s
-73 % vs Ø 3.406,7
Time to First Token 2.388 ms
-72 % vs Ø 8.418
Distribution in the field0 – 405 tok/s
Ø 128 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
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
NVIDIA-Nemotron-3-Nano-30B-A3BNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260729-032121-643b00
357,0 tok/s
Seed-OSS-36B-Instruct this runNVIDIA GeForce RTX 3090 Ti · run-20260729-105338-8d4996
16,7 tok/s

How does this benchmark compare on other GPUs?

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

Configuration

benchmark-konfiguration — run-20260729-105338-8d4996
# LLM-Benchmark Konfiguration # Modell : Seed-OSS-36B-Instruct # Engine : llama.cpp # Run-ID : run-20260729-105338-8d4996 # GPU : NVIDIA GeForce RTX 3090 Ti # CPU : AMD Ryzen 9 8945HX with Radeon Graphics # RAM : 92 GB bench@llm-benchmark:~$ /root/llama.cpp/build/bin/llama-server \ -m /root/.cache/huggingface/hub/models--yarikdevcom--Seed-OSS-36B-Instruct-GGUF/snapshots/cced0086e699de401821cce4b6fa69d3c6e87011/Seed_OSS_36B_Instruct_Q4_K_M.gguf \ --alias Seed-OSS-36B-Instruct \ --host 0.0.0.0 \ --port 8000 \ -ngl 60 \ -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.Seed-OSS-36B-Instruct
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--yarikdevcom--Seed-OSS-36B-Instruct-GGUF/snapshots/cced0086e699de401821cce4b6fa69d3c6e87011/Seed_OSS_36B_Instruct_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.60
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

Seed-OSS-36B-Instruct 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

5984482991490,001.2982.5953.893Prefill (tok/s)Generation (tok/s)NVIDIA RTX PRO 6000 Blackwell Workstation Edition - 460,0 tok/s Generation, 3.141 tok/s Prefill, TTFT 10.624 ms (3 Laufe)NVIDIA RTX PRO 6000 B...AMD Radeon AI PRO R9700 - 78,4 tok/s Generation, 2.174 tok/s Prefill, TTFT 7.389 ms (2 Laufe)AMD Radeon AI PRO R97...AMD Radeon 8060S Graphics - 43,0 tok/s Generation, 343 tok/s Prefill, TTFT 30.694 ms (3 Laufe)AMD Radeon 8060S Grap...NVIDIA GeForce RTX 5070 Ti - 39,2 tok/s Generation, 423 tok/s Prefill, TTFT 95.542 ms (3 Laufe)NVIDIA GeForce RTX 50...CPU-only - 1,0 tok/s Generation, 8 tok/s Prefill, TTFT 240.790 ms (1 Lauf)CPU-onlyNVIDIA GeForce RTX 3090 Ti - 111,6 tok/s Generation, 992 tok/s Prefill, TTFT 41.392 ms (3 Laufe) | DIESER LAUF★ NVIDIA GeForce RTX 30...
NVIDIA RTX PRO 6000 Blackwell Workstation Edition 460,0 tok/s★ NVIDIA GeForce RTX 3090 Ti 111,6 tok/s this runAMD Radeon AI PRO R9700 78,4 tok/sAMD Radeon 8060S Graphics 43,0 tok/sNVIDIA GeForce RTX 5070 Ti 39,2 tok/sCPU-only 1,0 tok/s

CPUby processor

5984482991490,001.2982.5953.893Prefill (tok/s)Generation (tok/s)AMD Ryzen 9 9950X 16-Core Processor - 460,0 tok/s Generation, 3.141 tok/s Prefill, TTFT 10.624 ms (3 Laufe)AMD Ryzen 9 9950X 16-...AMD Ryzen Threadripper PRO 7955WX 16-Cores - 78,4 tok/s Generation, 2.174 tok/s Prefill, TTFT 7.389 ms (2 Laufe)AMD Ryzen Threadrippe...AMD RYZEN AI MAX+ 395 w/ Radeon 8060S - 43,0 tok/s Generation, 343 tok/s Prefill, TTFT 30.694 ms (3 Laufe)AMD RYZEN AI MAX+ 395...AMD Ryzen Threadripper PRO 5975WX 32-Cores - 39,2 tok/s Generation, 423 tok/s Prefill, TTFT 95.542 ms (3 Laufe)AMD Ryzen Threadrippe...Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz - 1,0 tok/s Generation, 8 tok/s Prefill, TTFT 240.790 ms (1 Lauf)Intel(R) Xeon(R) CPU ...AMD Ryzen 9 8945HX with Radeon Graphics - 111,6 tok/s Generation, 992 tok/s Prefill, TTFT 41.392 ms (3 Laufe) | DIESER LAUF★ AMD Ryzen 9 8945HX wi...
AMD Ryzen 9 9950X 16-Core Processor 460,0 tok/s★ AMD Ryzen 9 8945HX with Radeon Graphics 111,6 tok/s this runAMD Ryzen Threadripper PRO 7955WX 16-Cores 78,4 tok/sAMD RYZEN AI MAX+ 395 w/ Radeon 8060S 43,0 tok/sAMD Ryzen Threadripper PRO 5975WX 32-Cores 39,2 tok/sIntel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz 1,0 tok/s

MBby mainboard

5984482991490,001.2982.5953.893Prefill (tok/s)Generation (tok/s)ASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI - 460,0 tok/s Generation, 3.141 tok/s Prefill, TTFT 10.624 ms (3 Laufe)ASUSTeK COMPUTER INC....ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE - 78,4 tok/s Generation, 2.174 tok/s Prefill, TTFT 7.389 ms (2 Laufe)ASUSTeK COMPUTER INC....Bosgame AXB35-02 (BeyondMax Series) - 43,0 tok/s Generation, 343 tok/s Prefill, TTFT 30.694 ms (3 Laufe)Bosgame AXB35-02 (Bey...ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI - 39,2 tok/s Generation, 423 tok/s Prefill, TTFT 95.542 ms (3 Laufe)ASUSTeK COMPUTER INC....Dell Inc. PowerEdge R820 - 1,0 tok/s Generation, 8 tok/s Prefill, TTFT 240.790 ms (1 Lauf)Dell Inc. PowerEdge R...Meigao Innovation Technology (Shen Zhen) Co., Ltd DRFXL (MotherBoard Series) - 111,6 tok/s Generation, 992 tok/s Prefill, TTFT 41.392 ms (3 Laufe) | DIESER LAUF★ Meigao Innovation Tec...
ASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI 460,0 tok/s★ Meigao Innovation Technology (Shen Zhen) Co., Ltd DRFXL (MotherBoard Series) 111,6 tok/s this runASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE 78,4 tok/sBosgame AXB35-02 (BeyondMax Series) 43,0 tok/sASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI 39,2 tok/sDell Inc. PowerEdge R820 1,0 tok/s

ENGby engine

5064834604374141.1941.2451.2951.346Prefill (tok/s)Generation (tok/s)llama.cpp - 460,0 tok/s Generation, 1.270 tok/s Prefill, TTFT 52.688 ms (15 Laufe) | DIESER LAUF★ llama.cpp
★ llama.cpp 460,0 tok/s this run

DRVby driver

5064834604374141.1941.2451.2951.346Prefill (tok/s)Generation (tok/s)unbekannt - 460,0 tok/s Generation, 1.270 tok/s Prefill, TTFT 52.688 ms (15 Laufe)unbekannt
unbekannt 460,0 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 URLReset
⚡ Electricity price EUR/kWh
⚙️ System utilization 100 %
🖥️ Acquisition EUR
🔌 Idle 50 W
⚡ TDP 477 W
☁️ External LLM (API)
Electricity0.30 EUR/kWh
Avg power (incl. idle)477 W estimated (TDP)GPU 450 + CPU 17 + Board 10 W full load
Avg cost / hourEUR 0.14
Electricity / 1M tokensEUR 2.38
Token / kWh125.97K
Acquisition (system)EUR 2,986 partial priceGPU EUR 999 · CPU EUR 549 · RAM EUR 1,288 · PSU EUR 150
Electricity (2 years)
TCO (2 years)EUR 5,494
Output tokens (2 years)1.05B
☁️ 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 (50 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

Seed-OSS-36B-InstructNVIDIA GeForce RTX 3090 TiSeed-OSS-36B-InstructNVIDIA RTX PRO 6000 Blackwell Workstation EditionSeed-OSS-36B-InstructAMD Radeon 8060S GraphicsSeed-OSS-36B-InstructNVIDIA GeForce RTX 5070 Ti
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.