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

DeepSeek-V4-Flash-284B-A13B

Performance benchmark · measured on 31.07.2026 11:30

Benchmark-IDrun-20260801-072827-bd2463
Timebench 3 - Kombi (Prefill + Generation)MoE284BRuntime: llama.cppQuantisierung: UD-Q4_K_XL
Generation206,50tok/s
Prefill2.079,51tok/s
Time to First Token10.488,50ms
Total duration100,27s
Concurrency5parallel
Ranking in the field
312of 563 systems

Performance benchmark · Primary metric: Generation-Speed (tok/s) · 5× concurrent

This run is better than 45 % of all comparable systems.
Generation 206,5 tok/s
-45 % vs Ø 375,2
Prefill 2.079,5 tok/s
-59 % vs Ø 5.125,5
Time to First Token 10.489 ms
-70 % vs Ø 34.589
Distribution in the field0 – 1.349 tok/s
Ø 371 Median Dieser Lauf

Wie schlägt sich dieser Benchmark mit anderen Modellen?

gemma-4-E2B-itNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260727-181606-0adf6d
1.349,3 tok/s
gemma-4-E2B-itNVIDIA GeForce RTX 5090 · run-20260728-184455-5b4937
1.301,9 tok/s
gemma-4-E2B-it3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-184456-4111a9
1.195,7 tok/s
NVIDIA-Nemotron-3-Nano-4BNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260727-181607-30d864
1.188,7 tok/s
NVIDIA-Nemotron-3-Nano-4BNVIDIA GeForce RTX 5090 · run-20260728-194135-5432cd
1.164,8 tok/s
gpt-oss-20bNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260728-140954-9e81f9
1.136,3 tok/s
gpt-oss-20bNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260730-035052-09627f
1.135,0 tok/s
gpt-oss-20bNVIDIA GeForce RTX 5090 · run-20260729-032121-058a31
1.113,5 tok/s
NVIDIA-Nemotron-3-Nano-4B3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-194136-836a91
1.090,6 tok/s
NVIDIA-Nemotron-3-Nano-4B3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260727-181606-8b381e
1.077,4 tok/s
NVIDIA-Nemotron-3-Nano-4B3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-194136-b8a818
1.071,0 tok/s
NVIDIA-Nemotron-3-Nano-4B3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-194136-038e92
1.051,1 tok/s
gpt-oss-20b3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260729-032121-ffb18a
1.015,5 tok/s
NVIDIA-Nemotron-3-Nano-30B-A3BNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260729-032121-305ad6
1.007,8 tok/s
DeepSeek-V4-Flash-284B-A13B this run3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260801-072827-bd2463
206,5 tok/s

How does this benchmark compare on other GPUs?

Same model on different hardware · 5× concurrent · Generation (tok/s)

Hardware

GPU: 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · 96 GB VRAM
CPU: AMD Ryzen Threadripper PRO 9965WX 24-Cores
RAM: 125 GB
Mainboard: ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE

Setup

Runtime: llama.cpp
Quantization: UD-Q4_K_XL
Model: DeepSeek-V4-Flash-284B-A13B

Configuration

benchmark-konfiguration — run-20260801-072827-bd2463
# LLM-Benchmark Konfiguration # Modell : DeepSeek-V4-Flash-284B-A13B # Engine : llama.cpp # Run-ID : run-20260801-072827-bd2463 # GPU : 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition # CPU : AMD Ryzen Threadripper PRO 9965WX 24-Cores # RAM : 125 GB bench@llm-benchmark:~$ /home/godcore/llama.cpp/build/bin/llama-server \ -m /home/godcore/.cache/huggingface/hub/models--unsloth--DeepSeek-V4-Flash-GGUF/snapshots/e3aa0d6a5fa4f820d9e132ac1fd1d01e1b2b49e0/UD-Q4_K_XL/DeepSeek-V4-Flash-UD-Q4_K_XL-00001-of-00005.gguf \ --alias DeepSeek-V4-Flash-284B-A13B \ --host 0.0.0.0 \ --port 8000 \ -ngl 999 \ -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.DeepSeek-V4-Flash-284B-A13B
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--DeepSeek-V4-Flash-GGUF/snapshots/e3aa0d6a5fa4f820d9e132ac1fd1d01e1b2b49e0/UD-Q4_K_XL/DeepSeek-V4-Flash-UD-Q4_K_XL-00001-of-00005.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.16384
np4

All benchmarks of this model To leaderboard

Anzeige
Model comparison

DeepSeek-V4-Flash-284B-A13B 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

5013762511250,005691.1391.708Prefill (tok/s)Generation (tok/s)AMD Radeon AI PRO R9700 - 22,3 tok/s Generation, 179 tok/s Prefill, TTFT 90.211 ms (2 Laufe)AMD Radeon AI PRO R97...NVIDIA GeForce RTX 5070 Ti - 10,0 tok/s Generation, 69 tok/s Prefill, TTFT 132.055 ms (3 Laufe)NVIDIA GeForce RTX 50...NVIDIA GeForce RTX 5090 - 3,2 tok/s Generation, 27 tok/s Prefill, TTFT 240.091 ms (3 Laufe)NVIDIA GeForce RTX 50...CPU-only - 1,2 tok/s Generation, 14 tok/s Prefill, TTFT 148.315 ms (1 Lauf)CPU-onlyNVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition - 385,9 tok/s Generation, 1.380 tok/s Prefill, TTFT 72.450 ms (9 Laufe) | DIESER LAUF★ NVIDIA RTX PRO 6000 B...
★ NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 385,9 tok/s this runAMD Radeon AI PRO R9700 22,3 tok/sNVIDIA GeForce RTX 5070 Ti 10,0 tok/sNVIDIA GeForce RTX 5090 3,2 tok/sCPU-only 1,2 tok/s

CPUby processor

5013762511250,005691.1391.708Prefill (tok/s)Generation (tok/s)AMD Ryzen Threadripper PRO 7955WX 16-Cores - 22,3 tok/s Generation, 179 tok/s Prefill, TTFT 90.211 ms (2 Laufe)AMD Ryzen Threadrippe...AMD Ryzen Threadripper PRO 5975WX 32-Cores - 10,0 tok/s Generation, 69 tok/s Prefill, TTFT 132.055 ms (3 Laufe)AMD Ryzen Threadrippe...AMD Ryzen 7 5800X3D 8-Core Processor - 3,2 tok/s Generation, 27 tok/s Prefill, TTFT 240.091 ms (3 Laufe)AMD Ryzen 7 5800X3D 8...Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz - 1,2 tok/s Generation, 14 tok/s Prefill, TTFT 148.315 ms (1 Lauf)Intel(R) Xeon(R) CPU ...AMD Ryzen Threadripper PRO 9965WX 24-Cores - 385,9 tok/s Generation, 1.380 tok/s Prefill, TTFT 72.450 ms (9 Laufe) | DIESER LAUF★ AMD Ryzen Threadrippe...
★ AMD Ryzen Threadripper PRO 9965WX 24-Cores 385,9 tok/s this runAMD Ryzen Threadripper PRO 7955WX 16-Cores 22,3 tok/sAMD Ryzen Threadripper PRO 5975WX 32-Cores 10,0 tok/sAMD Ryzen 7 5800X3D 8-Core Processor 3,2 tok/sIntel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz 1,2 tok/s

MBby mainboard

5013762511250,004799581.437Prefill (tok/s)Generation (tok/s)ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI - 10,0 tok/s Generation, 69 tok/s Prefill, TTFT 132.055 ms (3 Laufe)ASUSTeK COMPUTER INC....ASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING - 3,2 tok/s Generation, 27 tok/s Prefill, TTFT 240.091 ms (3 Laufe)ASUSTeK COMPUTER INC....Dell Inc. PowerEdge R820 - 1,2 tok/s Generation, 14 tok/s Prefill, TTFT 148.315 ms (1 Lauf)Dell Inc. PowerEdge R...ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE - 385,9 tok/s Generation, 1.161 tok/s Prefill, TTFT 75.679 ms (11 Laufe) | DIESER LAUF★ ASUSTeK COMPUTER INC....
★ ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE 385,9 tok/s this runASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI 10,0 tok/sASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING 3,2 tok/sDell Inc. PowerEdge R820 1,2 tok/s

ENGby engine

425405386367347683712741770Prefill (tok/s)Generation (tok/s)llama.cpp - 385,9 tok/s Generation, 727 tok/s Prefill, TTFT 116.512 ms (18 Laufe) | DIESER LAUF★ llama.cpp
★ llama.cpp 385,9 tok/s this run

DRVby driver

425405386367347683712741770Prefill (tok/s)Generation (tok/s)unbekannt - 385,9 tok/s Generation, 727 tok/s Prefill, TTFT 116.512 ms (18 Laufe)unbekannt
unbekannt 385,9 tok/s
💰 Economics

Economics of this run

Operating cost, TCO and comparison with the next-best runs of the same model at identical concurrency (5× 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 165 W
⚡ TDP 983 W
☁️ External LLM (API)
Electricity0.30 EUR/kWh
Avg power (incl. idle)983 W estimated (TDP)GPU 900 + CPU 57 + Board 25 W full load
Avg cost / hourEUR 0.29
Electricity / 1M tokensEUR 0.40
Token / kWh756.64K
Acquisition (system)EUR 45,748 full priceGPU EUR 39,000 · CPU EUR 3,499 · Board EUR 1,299 · RAM EUR 1,750 · PSU EUR 200
Electricity (2 years)
TCO (2 years)EUR 50,912
Output tokens (2 years)13.02B
☁️ 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 (165 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

DeepSeek-V4-Flash-284B-A13B3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionDeepSeek-V4-Flash-284B-A13B3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionDeepSeek-V4-Flash-284B-A13B3x AMD Radeon AI PRO R9700DeepSeek-V4-Flash-284B-A13BNVIDIA 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.