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

Mistral-Small-3.1-24B-Instruct-2503

Performance benchmark · measured on 29.08.2026 11:15

Benchmark-IDrun-20260829-092215-24c8f3
Timebench 3 - Kombi (Prefill + Generation)Dense24BRuntime: llama.cppQuantisierung: Q8_0
Generation29,63tok/s
Prefill581,77tok/s
Time to First Token3.807,00ms
Total duration50,15s
Concurrency1parallel
Ranking in the field
876of 1411 systems

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

This run is better than 38 % of all comparable systems.
Generation 29,6 tok/s
-62 % vs Ø 78,1
Prefill 581,8 tok/s
-79 % vs Ø 2.735,3
Time to First Token 3.807 ms
-87 % vs Ø 29.495
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 Radeon PRO W7800 48GB · 48 GB VRAM
CPU: AMD Ryzen Threadripper PRO 5975WX 32-Cores
RAM: 62 GB
Mainboard: ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI

Setup

Runtime: llama.cpp
Quantization: Q8_0
Model: Mistral-Small-3.1-24B-Instruct-2503

Configuration

benchmark-konfiguration — run-20260829-092215-24c8f3
# LLM-Benchmark Konfiguration # Modell : Mistral-Small-3.1-24B-Instruct-2503 # Engine : llama.cpp # Run-ID : run-20260829-092215-24c8f3 # GPU : AMD Radeon PRO W7800 48GB # CPU : AMD Ryzen Threadripper PRO 5975WX 32-Cores # RAM : 62 GB bench@llm-benchmark:~$ /home/godcore/llama.cpp/build_rocm/bin/llama-server \ -m mistralai_Mistral-Small-3.1-24B-Instruct-2503-Q8_0.gguf \ -ngl 999 \ -fa on \ -c 32768 \ -np 8 '(AMD' Radeon Pro W7800 48GB 'ROCm)'
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.mistralai_Mistral-Small-3.1-24B-Instruct-2503-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
np8

All benchmarks of this model To leaderboard

Anzeige
Model comparison

Mistral-Small-3.1-24B-Instruct-2503 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

27020313567,60,003.4356.87110.306Prefill (tok/s)Generation (tok/s)NVIDIA RTX A6000 - 211,5 tok/s Generation, 4.156 tok/s Prefill, TTFT 4.547 ms (21 Laufe)NVIDIA RTX A6000AMD Radeon PRO W7900 Dual Slot - 150,4 tok/s Generation, 1.883 tok/s Prefill, TTFT 8.173 ms (12 Laufe)AMD Radeon PRO W7900 ...NVIDIA RTX PRO 6000 Blackwell Workstation Edition - 88,3 tok/s Generation, 8.343 tok/s Prefill, TTFT 1.652 ms (3 Laufe)NVIDIA RTX PRO 6000 B...AMD Radeon AI PRO R9700 - 33,1 tok/s Generation, 3.057 tok/s Prefill, TTFT 1.231 ms (16 Laufe)AMD Radeon AI PRO R97...AMD Radeon 8060S Graphics - 31,3 tok/s Generation, 1.069 tok/s Prefill, TTFT 21.414 ms (2 Laufe)AMD Radeon 8060S Grap...NVIDIA Tesla P100 PCIe 16GB - 23,8 tok/s Generation, 218 tok/s Prefill, TTFT 30.869 ms (2 Laufe)NVIDIA Tesla P100 PCI...AMD Radeon PRO W7800 48GB - 29,6 tok/s Generation, 582 tok/s Prefill, TTFT 3.807 ms (1 Lauf) | DIESER LAUF★ AMD Radeon PRO W7800 ...
NVIDIA RTX A6000 211,5 tok/sAMD Radeon PRO W7900 Dual Slot 150,4 tok/sNVIDIA RTX PRO 6000 Blackwell Workstation Edition 88,3 tok/sAMD Radeon AI PRO R9700 33,1 tok/sAMD Radeon 8060S Graphics 31,3 tok/s★ AMD Radeon PRO W7800 48GB 29,6 tok/s this runNVIDIA Tesla P100 PCIe 16GB 23,8 tok/s

CPUby processor

27020313567,60,003.4356.87110.306Prefill (tok/s)Generation (tok/s)AMD Ryzen Threadripper PRO 7955WX 16-Cores - 211,5 tok/s Generation, 3.681 tok/s Prefill, TTFT 3.113 ms (37 Laufe)AMD Ryzen Threadrippe...AMD Ryzen 9 9950X 16-Core Processor - 88,3 tok/s Generation, 8.343 tok/s Prefill, TTFT 1.652 ms (3 Laufe)AMD Ryzen 9 9950X 16-...AMD RYZEN AI MAX+ 395 w/ Radeon 8060S - 31,3 tok/s Generation, 1.069 tok/s Prefill, TTFT 21.414 ms (2 Laufe)AMD RYZEN AI MAX+ 395...AMD Ryzen 9 7945HX with Radeon Graphics - 23,8 tok/s Generation, 218 tok/s Prefill, TTFT 30.869 ms (2 Laufe)AMD Ryzen 9 7945HX wi...AMD Ryzen Threadripper PRO 5975WX 32-Cores - 150,4 tok/s Generation, 1.783 tok/s Prefill, TTFT 7.837 ms (13 Laufe) | DIESER LAUF★ AMD Ryzen Threadrippe...
AMD Ryzen Threadripper PRO 7955WX 16-Cores 211,5 tok/s★ AMD Ryzen Threadripper PRO 5975WX 32-Cores 150,4 tok/s this runAMD Ryzen 9 9950X 16-Core Processor 88,3 tok/sAMD RYZEN AI MAX+ 395 w/ Radeon 8060S 31,3 tok/sAMD Ryzen 9 7945HX with Radeon Graphics 23,8 tok/s

MBby mainboard

27020313567,60,003.4356.87110.306Prefill (tok/s)Generation (tok/s)ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE - 211,5 tok/s Generation, 3.681 tok/s Prefill, TTFT 3.113 ms (37 Laufe)ASUSTeK COMPUTER INC....ASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI - 88,3 tok/s Generation, 8.343 tok/s Prefill, TTFT 1.652 ms (3 Laufe)ASUSTeK COMPUTER INC....Bosgame AXB35-02 (BeyondMax Series) - 31,3 tok/s Generation, 1.069 tok/s Prefill, TTFT 21.414 ms (2 Laufe)Bosgame AXB35-02 (Bey...Shenzhen Meigao Electronic Equipment Co.,Ltd F1FXM (DeskMini Series) - 23,8 tok/s Generation, 218 tok/s Prefill, TTFT 30.869 ms (2 Laufe)Shenzhen Meigao Elect...ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI - 150,4 tok/s Generation, 1.783 tok/s Prefill, TTFT 7.837 ms (13 Laufe) | DIESER LAUF★ ASUSTeK COMPUTER INC....
ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE 211,5 tok/s★ ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI 150,4 tok/s this runASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI 88,3 tok/sBosgame AXB35-02 (BeyondMax Series) 31,3 tok/sShenzhen Meigao Electronic Equipment Co.,Ltd F1FXM (DeskMini Series) 23,8 tok/s

ENGby engine

26820113467,10,08603.0515.2417.431Prefill (tok/s)Generation (tok/s)vLLM - 99,3 tok/s Generation, 6.284 tok/s Prefill, TTFT 2.012 ms (15 Laufe)vLLMunbekannt - 33,1 tok/s Generation, 3.057 tok/s Prefill, TTFT 1.231 ms (8 Laufe)unbekanntllama.cpp - 211,5 tok/s Generation, 2.007 tok/s Prefill, TTFT 8.428 ms (34 Laufe) | DIESER LAUF★ llama.cpp
★ llama.cpp 211,5 tok/s this runvLLM 99,3 tok/sunbekannt 33,1 tok/s

DRVby driver

26820113467,10,02.8113.0623.3123.562Prefill (tok/s)Generation (tok/s)unbekannt - 211,5 tok/s Generation, 3.316 tok/s Prefill, TTFT 6.464 ms (49 Laufe)unbekanntAMD 7.0.0-27-generic - 33,1 tok/s Generation, 3.057 tok/s Prefill, TTFT 1.231 ms (8 Laufe)AMD 7.0.0-27-generic
unbekannt 211,5 tok/sAMD 7.0.0-27-generic 33,1 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 270 W
☁️ External LLM (API)
Electricity0.30 EUR/kWh
Avg power (incl. idle)270 W estimated (TDP)GPU 260 + Board 10 W full load
Avg cost / hourEUR 0.081
Electricity / 1M tokensEUR 0.76
Token / kWh395.07K
Acquisition (system)EUR 5,304 partial priceGPU EUR 2,808 · CPU EUR 1,880 · RAM EUR 496 · PSU EUR 120
Electricity (2 years)
TCO (2 years)EUR 6,723
Output tokens (2 years)1.87B
☁️ 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

Mistral-Small-3.1-24B-Instruct-2503AMD Radeon PRO W7800 48GBMistral-Small-3.1-24B-Instruct-2503AMD Radeon PRO W7900 Dual SlotMistral-Small-3.1-24B-Instruct-25032x NVIDIA RTX A6000Mistral-Small-3.1-24B-Instruct-25032x AMD Radeon PRO W7900 Dual Slot
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.