Created bymario-alka.dePowered bygodcore.denoob2claw.detricoma.de
DEEN
Sign in Sign up
Beta
Contributed byMario AlkaDeepSeek

DeepSeek-V4-Flash-284B-A13B

Performance benchmark · measured on 30.07.2026 16:05

Benchmark-IDrun-20260730-181639-7bd0d6
Timebench 3 - Kombi (Prefill + Generation)MoE284BRuntime: llama.cppQuantisierung: UD-Q4_K_XL
Generation4,29tok/s
Prefill65,06tok/s
Time to First Token35.268,00ms
Total duration548,52s
Concurrency1parallel
Ranking in the field
This GPUAll GPUs
66of 71 systems

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

This run is better than 7 % of all comparable systems.
Generation 4,3 tok/s
-92 % vs Ø 51,5
Prefill 65,1 tok/s
-95 % vs Ø 1.269,7
Time to First Token 35.268 ms
+233 % vs Ø 10.601
Distribution in the field1 – 276 tok/s
Ø 51 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)

NVIDIA GeForce RTX 5070 Ti this runrun-20260730-181639-7bd0d6
4,3 tok/s
Keine GPU (CPU-only)run-20260723-114455-5b9033
1,2 tok/s

Hardware

GPU: NVIDIA GeForce RTX 5070 Ti · 16 GB VRAM
CPU: AMD Ryzen Threadripper PRO 5975WX 32-Cores
RAM: 247 GB
Mainboard: ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI

Setup

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

Configuration

benchmark-konfiguration — run-20260730-181639-7bd0d6
# LLM-Benchmark Konfiguration # Modell : DeepSeek-V4-Flash-284B-A13B # Engine : llama.cpp # Run-ID : run-20260730-181639-7bd0d6 # GPU : NVIDIA GeForce RTX 5070 Ti # CPU : AMD Ryzen Threadripper PRO 5975WX 32-Cores # RAM : 247 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 0 \ -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.0
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

28,721,514,47,20,0073146219Prefill (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...CPU-only - 1,2 tok/s Generation, 14 tok/s Prefill, TTFT 148.315 ms (1 Lauf)CPU-onlyNVIDIA GeForce RTX 5070 Ti - 10,0 tok/s Generation, 69 tok/s Prefill, TTFT 132.055 ms (3 Laufe) | DIESER LAUF★ NVIDIA GeForce RTX 50...
AMD Radeon AI PRO R9700 22,3 tok/s★ NVIDIA GeForce RTX 5070 Ti 10,0 tok/s this runCPU-only 1,2 tok/s

CPUby processor

28,721,514,47,20,0073146219Prefill (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...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 5975WX 32-Cores - 10,0 tok/s Generation, 69 tok/s Prefill, TTFT 132.055 ms (3 Laufe) | DIESER LAUF★ AMD Ryzen Threadrippe...
AMD Ryzen Threadripper PRO 7955WX 16-Cores 22,3 tok/s★ AMD Ryzen Threadripper PRO 5975WX 32-Cores 10,0 tok/s this runIntel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz 1,2 tok/s

MBby mainboard

28,721,514,47,20,0073146219Prefill (tok/s)Generation (tok/s)ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE - 22,3 tok/s Generation, 179 tok/s Prefill, TTFT 90.211 ms (2 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 WRX80E-SAGE SE WIFI - 10,0 tok/s Generation, 69 tok/s Prefill, TTFT 132.055 ms (3 Laufe) | DIESER LAUF★ ASUSTeK COMPUTER INC....
ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE 22,3 tok/s★ ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI 10,0 tok/s this runDell Inc. PowerEdge R820 1,2 tok/s

ENGby engine

24,523,422,321,220,0919498102Prefill (tok/s)Generation (tok/s)llama.cpp - 22,3 tok/s Generation, 96 tok/s Prefill, TTFT 120.817 ms (6 Laufe) | DIESER LAUF★ llama.cpp
★ llama.cpp 22,3 tok/s this run

DRVby driver

24,523,422,321,220,0919498102Prefill (tok/s)Generation (tok/s)unbekannt - 22,3 tok/s Generation, 96 tok/s Prefill, TTFT 120.817 ms (6 Laufe)unbekannt
unbekannt 22,3 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 10 W
⚡ TDP 310 W
☁️ External LLM (API)
Electricity0.30 EUR/kWh
Avg power (incl. idle)310 W estimated (TDP)GPU 300 + Board 10 W full load
Avg cost / hourEUR 0.093
Electricity / 1M tokensEUR 6.02
Token / kWh49.82K
Acquisition (system)EUR 2,126 missingRAM EUR 1,976 · PSU EUR 150
Electricity (2 years)–
TCO (2 years)EUR 3,755
Output tokens (2 years)270.58M
☁️ 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 (10 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-A13BNVIDIA GeForce RTX 5070 TiDeepSeek-V4-Flash-284B-A13BKeine GPU (CPU-only)
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)––
NVIDIA GeForce RTX 5070 Ti · this run 4 tok/sKeine GPU (CPU-only) 1 tok/s

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.