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

Seed-OSS-36B-Instruct

Performance benchmark · measured on 23.07.2026 14:42

Benchmark-IDrun-20260723-174503-613547
Timebench 3 - Kombi (Prefill + Generation)Runtime: 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.
Generation9,63tok/s
Prefill280,01tok/s
Time to First Token7.000,00ms
Total duration42,75s
Concurrency1parallel
Ranking in the field
933of 997 systems

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

This run is better than 6 % of all comparable systems.
Generation 9,6 tok/s
-96 % vs Ø 270,4
Prefill 280,0 tok/s
-95 % vs Ø 5.568,2
Time to First Token 7.000 ms
-28 % vs Ø 9.777
Distribution in the field0 – 1.444 tok/s
Ø 270 Median Dieser Lauf

Wie schlägt sich dieser Benchmark?

gpt-oss-20bNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260723-194447-dc199d
1.443,9 tok/s
gpt-oss-20bNVIDIA GeForce RTX 5090 · run-20260724-004604-1c9023
1.386,8 tok/s
Qwen2.5-Coder-32B-InstructNVIDIA GeForce RTX 5090 · run-20260724-082948-5b32df
1.307,9 tok/s
gpt-oss-20bNVIDIA GeForce RTX 5090 · run-20260723-045447-edeed3
1.295,3 tok/s
gpt-oss-20b3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260724-082940-10761f
1.238,3 tok/s
Qwen3-Coder-30B-A3B-InstructNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260724-004606-ebf474
1.070,6 tok/s
Qwen3.5-35B-A3BNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260724-082959-cd1403
1.028,6 tok/s
Qwen3-VL-30B-A3B-InstructNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260724-004607-c49303
1.028,5 tok/s
Ministral-3-14B-Reasoning-2512NVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260723-195749-eebab2
1.015,7 tok/s
GLM-4.5-AirNVIDIA GeForce RTX 5090 · run-20260724-082959-2ea391
976,7 tok/s
Qwen3-Coder-30B-A3B-InstructNVIDIA GeForce RTX 5090 · run-20260723-045450-366dae
966,2 tok/s
Qwen3-30B-A3B-Instruct-2507NVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260724-004604-860045
961,5 tok/s
Devstral-Small-2507NVIDIA GeForce RTX 5090 · run-20260724-082938-ad06f1
958,9 tok/s
Qwen3.6-35B-A3BNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260724-083000-8690d7
952,8 tok/s
Seed-OSS-36B-Instruct this runAMD Radeon 8060S Graphics · run-20260723-174503-613547
9,6 tok/s

Hardware

GPU: AMD Radeon 8060S Graphics
CPU: 32x AMD RYZEN AI MAX+ 395 w/ Radeon 8060S
RAM: 31 GB
Mainboard: Meigao Innovation Technology (Shen Zhen) Co., Ltd SHWSA (MS-S1 MAX)

Setup

Runtime: llama.cpp
Quantization: Q4_K_M
Operating system: Ubuntu 24.04.2 LTS (Kernel 6.17.0-40-generic)
Driver: ROCm 7.2.0
Model: Seed-OSS-36B-Instruct

Configuration

benchmark-konfiguration — run-20260723-174503-613547
# LLM-Benchmark Konfiguration # Modell : Seed-OSS-36B-Instruct # Engine : llama.cpp # Run-ID : run-20260723-174503-613547 # GPU : AMD Radeon 8060S Graphics # CPU : 32x AMD RYZEN AI MAX+ 395 w/ Radeon 8060S # RAM : 31 GB bench@llm-benchmark:~$ llama-server \ -m yarikdevcom/Seed-OSS-36B-Instruct-GGUF/Q4_K_M.gguf \ -a Seed-OSS-36B-Instruct \ --host 0.0.0.0 \ --port 8000 \ --gpu-layers 99 \ --flash-attn on \ -c 26624 \ --parallel 12
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.26624
Modellpfad?Pfad zur GGUF-Modelldatei, die geladen und ausgeliefert wird.yarikdevcom/Seed-OSS-36B-Instruct-GGUF/Q4_K_M.gguf
Alias?Anzeigename des Modells nach aussen (served model name), unabhaengig vom Dateinamen.Seed-OSS-36B-Instruct
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.99
Flash Attention?FlashAttention fuer schnellere und speichersparende Attention. Wert on/off/auto je nach Build.on
Kontext?Groesse des Kontextfensters in Token. 0 = der beim Training verwendete Kontext des Modells.26624
Parallel?Anzahl paralleler Slots/Sequenzen, die der Server gleichzeitig bedient. Der Kontext wird auf die Slots aufgeteilt.12

All benchmarks of this model To leaderboard

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

10276,250,825,40,007511.5022.254Prefill (tok/s)Generation (tok/s)AMD Radeon AI PRO R9700 - 78,4 tok/s Generation, 1.819 tok/s Prefill, TTFT 5.620 ms (3 Laufe)AMD Radeon AI PRO R97...CPU-only - 1,0 tok/s Generation, 8 tok/s Prefill, TTFT 240.790 ms (1 Lauf)CPU-onlyAMD Radeon 8060S Graphics - 43,0 tok/s Generation, 343 tok/s Prefill, TTFT 30.694 ms (3 Laufe) | DIESER LAUF★ AMD Radeon 8060S Grap...
AMD Radeon AI PRO R9700 78,4 tok/s★ AMD Radeon 8060S Graphics 43,0 tok/s this runCPU-only 1,0 tok/s

CPUby processor

10276,250,825,40,007511.5022.254Prefill (tok/s)Generation (tok/s)AMD Ryzen Threadripper PRO 7955WX 16-Cores - 78,4 tok/s Generation, 1.819 tok/s Prefill, TTFT 5.620 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 AI MAX+ 395 w/ Radeon 8060S - 43,0 tok/s Generation, 343 tok/s Prefill, TTFT 30.694 ms (3 Laufe) | DIESER LAUF★ AMD RYZEN AI MAX+ 395...
AMD Ryzen Threadripper PRO 7955WX 16-Cores 78,4 tok/s★ AMD RYZEN AI MAX+ 395 w/ Radeon 8060S 43,0 tok/s this runIntel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz 1,0 tok/s

MBby mainboard

10276,250,825,40,007511.5022.254Prefill (tok/s)Generation (tok/s)ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE - 78,4 tok/s Generation, 1.819 tok/s Prefill, TTFT 5.620 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 SHWSA (MS-S1 MAX) - 43,0 tok/s Generation, 343 tok/s Prefill, TTFT 30.694 ms (3 Laufe) | DIESER LAUF★ Meigao Innovation Tec...
ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE 78,4 tok/s★ Meigao Innovation Technology (Shen Zhen) Co., Ltd SHWSA (MS-S1 MAX) 43,0 tok/s this runDell Inc. PowerEdge R820 1,0 tok/s

ENGby engine

86,282,378,474,470,5872909946983Prefill (tok/s)Generation (tok/s)llama.cpp - 78,4 tok/s Generation, 928 tok/s Prefill, TTFT 49.962 ms (7 Laufe) | DIESER LAUF★ llama.cpp
★ llama.cpp 78,4 tok/s this run

DRVby driver

10276,250,825,40,007511.5022.254Prefill (tok/s)Generation (tok/s)AMD 7.0.0-27-generic - 78,4 tok/s Generation, 1.819 tok/s Prefill, TTFT 5.620 ms (3 Laufe)AMD 7.0.0-27-genericunbekannt - 1,0 tok/s Generation, 8 tok/s Prefill, TTFT 240.790 ms (1 Lauf)unbekanntROCm 7.2.0 - 43,0 tok/s Generation, 343 tok/s Prefill, TTFT 30.694 ms (3 Laufe) | DIESER LAUF★ ROCm 7.2.0
AMD 7.0.0-27-generic 78,4 tok/s★ ROCm 7.2.0 43,0 tok/s this rununbekannt 1,0 tok/s
Contributed by

Mario Alka Administrator

@marioalka

Gruender von godcore.de