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

DeepSeek-V4-Flash-284B-A13B

Performance benchmark · measured on 23.07.2026 10:50

Benchmark-IDrun-20260723-114455-5b9033
Timebench 3 - Kombi (Prefill + Generation)MoE284BRuntime: llama.cppQuantisierung: UD-Q4_K_XL
Generation1,20tok/s
Prefill14,29tok/s
Time to First Token148.314,50ms
Total duration600,00s
Concurrency1parallel
Ranking in the field
1491of 1549 systems

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

This run is better than 4 % of all comparable systems.
Generation 1,2 tok/s
-98 % vs Ø 79,0
Prefill 14,3 tok/s
-99 % vs Ø 2.837,1
Time to First Token 148.315 ms
+450 % vs Ø 26.963
Distribution in the field0 – 405 tok/s
Ø 79 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: 2x NVIDIA GeForce RTX 2060 · 6 GB VRAM
CPU: 4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz
RAM: 504 GB
Mainboard: Dell Inc. PowerEdge R820

Setup

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

Configuration

benchmark-konfiguration — run-20260723-114455-5b9033
# LLM-Benchmark Konfiguration # Modell : DeepSeek-V4-Flash-284B-A13B # Engine : llama.cpp # Run-ID : run-20260723-114455-5b9033 # GPU : 2x NVIDIA GeForce RTX 2060 # CPU : 4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz # RAM : 504 GB bench@llm-benchmark:~$ /opt/llama.cpp/build/bin/llama-server \ -m /opt/models/DeepSeek-V4-Flash-284B-A13B-Q4_K_M.gguf \ -a DeepSeek-V4-Flash-284B-A13B \ --host 0.0.0.0 \ --port 8080 \ --numa distribute \ -t 64 \ -tb 64 \ -c 8192 \ --parallel 4
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.8192
Modellpfad?Pfad zur GGUF-Modelldatei, die geladen und ausgeliefert wird./opt/models/DeepSeek-V4-Flash-284B-A13B-Q4_K_M.gguf
Alias?Anzeigename des Modells nach aussen (served model name), unabhaengig vom Dateinamen.DeepSeek-V4-Flash-284B-A13B
NUMA?NUMA-Optimierung fuer Multi-Socket-CPUs: distribute/isolate/numactl. Verbessert die Speicherlokalitaet.distribute
Threads?Anzahl CPU-Threads fuer die Token-Generierung (Decode).64
Batch-Threads?Anzahl CPU-Threads fuer Prompt-Verarbeitung und Batch (Prefill).64
Kontext?Groesse des Kontextfensters in Token. 0 = der beim Training verwendete Kontext des Modells.8192
Parallel?Anzahl paralleler Slots/Sequenzen, die der Server gleichzeitig bedient. Der Kontext wird auf die Slots aufgeteilt.4

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

5013762511250,008471.6952.542Prefill (tok/s)Generation (tok/s)NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition - 385,9 tok/s Generation, 2.052 tok/s Prefill, TTFT 13.971 ms (6 Laufe)NVIDIA RTX PRO 6000 B...AMD Radeon AI PRO R9700 - 18,8 tok/s Generation, 58 tok/s Prefill, TTFT 165.244 ms (10 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...NVIDIA GeForce RTX 2060 - 1,2 tok/s Generation, 14 tok/s Prefill, TTFT 148.315 ms (1 Lauf) | DIESER LAUF★ NVIDIA GeForce RTX 20...
NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 385,9 tok/sAMD Radeon AI PRO R9700 18,8 tok/sNVIDIA GeForce RTX 5070 Ti 10,0 tok/sNVIDIA GeForce RTX 5090 3,2 tok/s★ NVIDIA GeForce RTX 2060 1,2 tok/s this run

CPUby processor

5013762511250,008471.6952.542Prefill (tok/s)Generation (tok/s)AMD Ryzen Threadripper PRO 9965WX 24-Cores - 385,9 tok/s Generation, 2.052 tok/s Prefill, TTFT 13.971 ms (6 Laufe)AMD Ryzen Threadrippe...AMD Ryzen Threadripper PRO 7955WX 16-Cores - 18,8 tok/s Generation, 58 tok/s Prefill, TTFT 165.244 ms (10 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) | DIESER LAUF★ Intel(R) Xeon(R) CPU ...
AMD Ryzen Threadripper PRO 9965WX 24-Cores 385,9 tok/sAMD Ryzen Threadripper PRO 7955WX 16-Cores 18,8 tok/sAMD Ryzen Threadripper PRO 5975WX 32-Cores 10,0 tok/sAMD Ryzen 7 5800X3D 8-Core Processor 3,2 tok/s★ Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz 1,2 tok/s this run

MBby mainboard

5013762511250,00332665997Prefill (tok/s)Generation (tok/s)ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE - 385,9 tok/s Generation, 806 tok/s Prefill, TTFT 108.517 ms (16 Laufe)ASUSTeK COMPUTER INC....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) | DIESER LAUF★ Dell Inc. PowerEdge R...
ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE 385,9 tok/sASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI 10,0 tok/sASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING 3,2 tok/s★ Dell Inc. PowerEdge R820 1,2 tok/s this run

ENGby engine

425405386367347539562585608Prefill (tok/s)Generation (tok/s)llama.cpp - 385,9 tok/s Generation, 574 tok/s Prefill, TTFT 130.479 ms (23 Laufe) | DIESER LAUF★ llama.cpp
★ llama.cpp 385,9 tok/s this run

DRVby driver

425405386367347539562585608Prefill (tok/s)Generation (tok/s)unbekannt - 385,9 tok/s Generation, 574 tok/s Prefill, TTFT 130.479 ms (23 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 (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 55 W
⚡ TDP 359 W
☁️ External LLM (API)
Electricity0.30 EUR/kWh
Avg power (incl. idle)359 W estimated (TDP)GPU 320 + CPU 29 + Board 10 W full load
Avg cost / hourEUR 0.11
Electricity / 1M tokensEUR 24.91
Token / kWh12.04K
Acquisition (system)EUR 2,425 partial priceGPU EUR 220 · CPU EUR 39 · RAM EUR 2,016 · PSU EUR 150
Electricity (2 years)
TCO (2 years)EUR 4,311
Output tokens (2 years)75.69M
☁️ 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 (55 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-A13B2x NVIDIA GeForce RTX 2060DeepSeek-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 R9700
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.