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

Llama-3.2-1B-Instruct

Performance benchmark · measured on 25.09.2026 18:00

Benchmark-IDrun-20261003-073244-93d630
Timebench 3 - Kombi (Prefill + Generation)Dense1BRuntime: llama.cppQuantisierung: Q4_K_M
Generation3,91tok/s
Prefill193,26tok/s
Time to First Token12.786,00ms
Total duration555,61s
Concurrency1parallel
Ranking in the field
1544of 1704 systems

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

This run is better than 9 % of all comparable systems.
Generation 3,9 tok/s
-95 % vs Ø 78,3
Prefill 193,3 tok/s
-93 % vs Ø 2.873,1
Time to First Token 12.786 ms
-50 % vs Ø 25.743
Distribution in the field0 – 405 tok/s
Ø 78 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: AMD Liverpool (PlayStation 4)
CPU: AMD Jaguar 8-Core (PlayStation 4)
RAM: 5 GB

Setup

Runtime: llama.cpp
Quantization: Q4_K_M
Model: Llama-3.2-1B-Instruct

Configuration

benchmark-konfiguration — run-20261003-073244-93d630
# LLM-Benchmark Konfiguration # Modell : Llama-3.2-1B-Instruct # Engine : llama.cpp # Run-ID : run-20261003-073244-93d630 # GPU : AMD Liverpool (PlayStation 4) # CPU : AMD Jaguar 8-Core (PlayStation 4) # RAM : 5 GB bench@llm-benchmark:~$ llama-server \ -ngl 0 \ -c 4096 \ -np 1 \ -t 6 '(llama.cpp' Q4_K_M CPU-only '(Jaguar,' kein 'AVX2))'
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.4096
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.4096
np1
Threads?Anzahl CPU-Threads fuer die Token-Generierung (Decode).6
execution_typelocal

All benchmarks of this model To leaderboard

Anzeige
Model comparison

Llama-3.2-1B-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

9246934622310,0013.26726.53539.802Prefill (tok/s)Generation (tok/s)AMD Radeon RX 7900 XTX - 717,6 tok/s Generation, 32.133 tok/s Prefill, TTFT 493 ms (6 Laufe)AMD Radeon RX 7900 XTXAMD Liverpool (PlayStation 4) - 43,2 tok/s Generation, 237 tok/s Prefill, TTFT 10.796 ms (2 Laufe) | DIESER LAUF★ AMD Liverpool (PlaySt...
AMD Radeon RX 7900 XTX 717,6 tok/s★ AMD Liverpool (PlayStation 4) 43,2 tok/s this run

CPUby processor

9246934622310,0013.26726.53539.802Prefill (tok/s)Generation (tok/s)AMD Ryzen Threadripper PRO 3955WX 16-Cores - 717,6 tok/s Generation, 32.133 tok/s Prefill, TTFT 493 ms (6 Laufe)AMD Ryzen Threadrippe...AMD Jaguar 8-Core (PlayStation 4) - 43,2 tok/s Generation, 237 tok/s Prefill, TTFT 10.796 ms (2 Laufe) | DIESER LAUF★ AMD Jaguar 8-Core (Pl...
AMD Ryzen Threadripper PRO 3955WX 16-Cores 717,6 tok/s★ AMD Jaguar 8-Core (PlayStation 4) 43,2 tok/s this run

MBby mainboard

9246934622310,0013.26726.53539.802Prefill (tok/s)Generation (tok/s)ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI - 717,6 tok/s Generation, 32.133 tok/s Prefill, TTFT 493 ms (6 Laufe)ASUSTeK COMPUTER INC....unbekannt - 43,2 tok/s Generation, 237 tok/s Prefill, TTFT 10.796 ms (2 Laufe)unbekannt
ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI 717,6 tok/sunbekannt 43,2 tok/s

ENGby engine

79475070766462111.11521.44231.76842.095Prefill (tok/s)Generation (tok/s)vLLM - 717,6 tok/s Generation, 36.389 tok/s Prefill, TTFT 511 ms (3 Laufe)vLLMllama.cpp - 696,8 tok/s Generation, 16.821 tok/s Prefill, TTFT 4.603 ms (5 Laufe) | DIESER LAUF★ llama.cpp
vLLM 717,6 tok/s★ llama.cpp 696,8 tok/s this run

DRVby driver

78975371868264622.71023.67624.64225.609Prefill (tok/s)Generation (tok/s)unbekannt - 717,6 tok/s Generation, 24.159 tok/s Prefill, TTFT 3.068 ms (8 Laufe)unbekannt
unbekannt 717,6 tok/s
💰 Economics

Economics of this run

Operating cost, TCO and comparison with the next-best runs of the same model at identical concurrency (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 %
🔌 Idle 0 W
⚡ TDP 10 W
☁️ External LLM (API)
Electricity0.30 EUR/kWh
Avg power (incl. idle)0 W missing
Avg cost / hour–
Electricity / 1M tokens–
Token / kWh–
Acquisition (system)– missing
Electricity (2 years)–
TCO (2 years)–
Output tokens (2 years)246.61M
☁️ External LLM (API) – comparison
External LLM cost (2 years)–
Savings vs. external (2 years)–
No power draw measured – values estimated from GPU TDP + CPU (idle + 15 %) + board.

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 (0 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-3.2-1B-InstructAMD Liverpool (PlayStation 4)Llama-3.2-1B-Instruct2x AMD Radeon RX 7900 XTXLlama-3.2-1B-Instruct2x AMD Radeon RX 7900 XTXLlama-3.2-1B-InstructAMD Liverpool (PlayStation 4)
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.