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

Llama-3.2-3B-Instruct

Performance benchmark · measured on 16.09.2026 16:33

Benchmark-IDrun-20260918-121614-764655
Timebench 3 - Kombi (Prefill + Generation)Dense3BRuntime: llama.cppQuantisierung: Q8_0
Generation158,90tok/s
Prefill7.616,17tok/s
Time to First Token1.908,00ms
Total duration22,63s
Concurrency5parallel
Ranking in the field
660of 1246 systems

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

This run is better than 47 % of all comparable systems.
Generation 158,9 tok/s
-39 % vs Ø 258,5
Prefill 7.616,2 tok/s
+43 % vs Ø 5.310,9
Time to First Token 1.908 ms
-94 % vs Ø 30.663
Distribution in the field0 – 1.349 tok/s
Ø 258 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
Nemotron-3-Nano-4BNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260727-181607-30d864
1.188,7 tok/s
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
Nemotron-3-Nano-4B3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-194136-836a91
1.090,6 tok/s
Nemotron-3-Nano-4B3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260727-181606-8b381e
1.077,4 tok/s
Nemotron-3-Nano-4B3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-194136-b8a818
1.071,0 tok/s
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
Nemotron-3-Nano-30B-A3BNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260729-032121-305ad6
1.007,8 tok/s
Llama-3.2-3B-Instruct this run2× NVIDIA GeForce RTX 2060 · run-20260918-121614-764655
158,9 tok/s

Hardware

GPU: 2x NVIDIA GeForce RTX 2060 · 6 GB VRAM
CPU: 4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz
RAM: 504 GB
Mainboard: Dell Inc. PowerEdge R820

Setup

Runtime: llama.cpp
Quantization: Q8_0
Model: Llama-3.2-3B-Instruct

Configuration

benchmark-konfiguration — run-20260918-121614-764655
# LLM-Benchmark Konfiguration # Modell : Llama-3.2-3B-Instruct # Engine : llama.cpp # Run-ID : run-20260918-121614-764655 # GPU : 2x NVIDIA GeForce RTX 2060 # CPU : 4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz # RAM : 504 GB bench@llm-benchmark:~$ llama-server \ -m Llama-3.2-3B-Instruct-Q8_0.gguf \ -ngl 999 \ -fa on \ -c 32768 \ -np 12 \ -sm layer '(2x' RTX 2060 '6GB)'
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
Kontextlaenge?Maximale Anzahl Tokens (Eingabe + erzeugte Ausgabe zusammen), die das Modell pro Anfrage verarbeiten kann.32768
Modellpfad?Pfad zur GGUF-Modelldatei, die geladen und ausgeliefert wird.Llama-3.2-3B-Instruct-Q8_0.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
faon
Kontext?Groesse des Kontextfensters in Token. 0 = der beim Training verwendete Kontext des Modells.32768
np12
Split-Mode?Verteilung ueber mehrere GPUs: none (nur eine GPU), layer (Layer aufteilen) oder row (Tensoren zeilenweise).layer

All benchmarks of this model To leaderboard

Anzeige
Model comparison

Llama-3.2-3B-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

2492382272152046.5116.7887.0657.342Prefill (tok/s)Generation (tok/s)NVIDIA GeForce RTX 2060 - 226,6 tok/s Generation, 6.927 tok/s Prefill, TTFT 2.004 ms (6 Laufe) | DIESER LAUF★ NVIDIA GeForce RTX 20...
★ NVIDIA GeForce RTX 2060 226,6 tok/s this run

CPUby processor

2492382272152046.5116.7887.0657.342Prefill (tok/s)Generation (tok/s)Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz - 226,6 tok/s Generation, 6.927 tok/s Prefill, TTFT 2.004 ms (6 Laufe) | DIESER LAUF★ Intel(R) Xeon(R) CPU ...
★ Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz 226,6 tok/s this run

MBby mainboard

2492382272152046.5116.7887.0657.342Prefill (tok/s)Generation (tok/s)Dell Inc. PowerEdge R820 - 226,6 tok/s Generation, 6.927 tok/s Prefill, TTFT 2.004 ms (6 Laufe) | DIESER LAUF★ Dell Inc. PowerEdge R...
★ Dell Inc. PowerEdge R820 226,6 tok/s this run

ENGby engine

2492382272152046.5116.7887.0657.342Prefill (tok/s)Generation (tok/s)llama.cpp - 226,6 tok/s Generation, 6.927 tok/s Prefill, TTFT 2.004 ms (6 Laufe) | DIESER LAUF★ llama.cpp
★ llama.cpp 226,6 tok/s this run

DRVby driver

2492382272152046.5116.7887.0657.342Prefill (tok/s)Generation (tok/s)unbekannt - 226,6 tok/s Generation, 6.927 tok/s Prefill, TTFT 2.004 ms (6 Laufe)unbekannt
unbekannt 226,6 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 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 0.19
Token / kWh1.59M
Acquisition (system)EUR 2,445 partial priceGPU EUR 220 · CPU EUR 59 · RAM EUR 2,016 · PSU EUR 150
Electricity (2 years)
TCO (2 years)EUR 4,331
Output tokens (2 years)10.02B
☁️ 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 (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

Llama-3.2-3B-Instruct2x NVIDIA GeForce RTX 2060Llama-3.2-3B-Instruct2x NVIDIA GeForce RTX 2060
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.