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

Devstral-Small-2507

Performance benchmark · measured on 03.08.2026 07:33

Benchmark-IDrun-20260805-053358-0e75b3
Timebench 3 - Kombi (Prefill + Generation)Dense24BRuntime: llama.cppQuantisierung: Q4_K_M
Generation32,95tok/s
Prefill2.126,56tok/s
Time to First Token1.623,00ms
Total duration43,82s
Concurrency1parallel
Ranking in the field
43of 125 systems

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

This run is better than 66 % of all comparable systems.
Generation 33,0 tok/s
0 % vs Ø 33,0
Prefill 2.126,6 tok/s
+26 % vs Ø 1.692,2
Time to First Token 1.623 ms
-93 % vs Ø 22.553
Distribution in the field1 – 140 tok/s
Ø 33 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: 3x AMD Radeon AI PRO R9700 · 32 GB VRAM
CPU: AMD Ryzen Threadripper PRO 7955WX 16-Cores
RAM: 184 GB
Mainboard: ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE

Setup

Runtime: llama.cpp
Quantization: Q4_K_M
Model: Devstral-Small-2507

Configuration

benchmark-konfiguration — run-20260805-053358-0e75b3
# LLM-Benchmark Konfiguration # Modell : Devstral-Small-2507 # Engine : llama.cpp # Run-ID : run-20260805-053358-0e75b3 # GPU : 3x AMD Radeon AI PRO R9700 # CPU : AMD Ryzen Threadripper PRO 7955WX 16-Cores # RAM : 184 GB bench@llm-benchmark:~$ /home/godcore/llama.cpp/build/bin/llama-server \ -m /home/godcore/.cache/huggingface/hub/models--mistralai--Devstral-Small-2507_gguf/snapshots/ee2f0c00c5c86862f471fbf533268cf01b80d4a6/Devstral-Small-2507-Q4_K_M.gguf \ --alias Devstral-Small-2507 \ --host 0.0.0.0 \ --port 8000 \ -ngl 999 \ -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.Devstral-Small-2507
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--mistralai--Devstral-Small-2507_gguf/snapshots/ee2f0c00c5c86862f471fbf533268cf01b80d4a6/Devstral-Small-2507-Q4_K_M.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
Kontext?Groesse des Kontextfensters in Token. 0 = der beim Training verwendete Kontext des Modells.16384
np4

All benchmarks of this model To leaderboard

Anzeige
Videoreihe und Benchmarkauswertung zur AMD R9700
Model comparison

Devstral-Small-2507 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

8216164112050,02554.6339.01213.391Prefill (tok/s)Generation (tok/s)NVIDIA RTX PRO 6000 Blackwell Workstation Edition - 647,6 tok/s Generation, 8.500 tok/s Prefill, TTFT 5.252 ms (3 Laufe)NVIDIA RTX PRO 6000 B...NVIDIA GeForce RTX 5090 - 625,1 tok/s Generation, 7.381 tok/s Prefill, TTFT 5.802 ms (3 Laufe)NVIDIA GeForce RTX 50...NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition - 572,2 tok/s Generation, 11.160 tok/s Prefill, TTFT 5.760 ms (12 Laufe)NVIDIA RTX PRO 6000 B...NVIDIA GeForce RTX 3090 Ti - 317,4 tok/s Generation, 2.986 tok/s Prefill, TTFT 8.212 ms (6 Laufe)NVIDIA GeForce RTX 30...NVIDIA GeForce RTX 5070 Ti - 103,9 tok/s Generation, 2.486 tok/s Prefill, TTFT 34.598 ms (5 Laufe)NVIDIA GeForce RTX 50...AMD Radeon AI PRO R9700 - 205,8 tok/s Generation, 4.532 tok/s Prefill, TTFT 15.384 ms (9 Laufe) | DIESER LAUF★ AMD Radeon AI PRO R97...
NVIDIA RTX PRO 6000 Blackwell Workstation Edition 647,6 tok/sNVIDIA GeForce RTX 5090 625,1 tok/sNVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 572,2 tok/sNVIDIA GeForce RTX 3090 Ti 317,4 tok/s★ AMD Radeon AI PRO R9700 205,8 tok/s this runNVIDIA GeForce RTX 5070 Ti 103,9 tok/s

CPUby processor

8306234152080,004.5329.06313.595Prefill (tok/s)Generation (tok/s)AMD Ryzen 9 9950X 16-Core Processor - 647,6 tok/s Generation, 8.500 tok/s Prefill, TTFT 5.252 ms (3 Laufe)AMD Ryzen 9 9950X 16-...AMD Ryzen 7 5800X3D 8-Core Processor - 625,1 tok/s Generation, 7.381 tok/s Prefill, TTFT 5.802 ms (3 Laufe)AMD Ryzen 7 5800X3D 8...AMD Ryzen Threadripper PRO 9965WX 24-Cores - 572,2 tok/s Generation, 11.160 tok/s Prefill, TTFT 5.760 ms (12 Laufe)AMD Ryzen Threadrippe...AMD Ryzen 9 8945HX with Radeon Graphics - 317,4 tok/s Generation, 4.619 tok/s Prefill, TTFT 10.835 ms (3 Laufe)AMD Ryzen 9 8945HX wi...AMD Ryzen Threadripper PRO 5975WX 32-Cores - 103,9 tok/s Generation, 2.486 tok/s Prefill, TTFT 34.598 ms (5 Laufe)AMD Ryzen Threadrippe...AMD Ryzen 5 5600X 6-Core Processor - 57,1 tok/s Generation, 1.354 tok/s Prefill, TTFT 5.590 ms (3 Laufe)AMD Ryzen 5 5600X 6-C...AMD Ryzen Threadripper PRO 7955WX 16-Cores - 205,8 tok/s Generation, 4.532 tok/s Prefill, TTFT 15.384 ms (9 Laufe) | DIESER LAUF★ AMD Ryzen Threadrippe...
AMD Ryzen 9 9950X 16-Core Processor 647,6 tok/sAMD Ryzen 7 5800X3D 8-Core Processor 625,1 tok/sAMD Ryzen Threadripper PRO 9965WX 24-Cores 572,2 tok/sAMD Ryzen 9 8945HX with Radeon Graphics 317,4 tok/s★ AMD Ryzen Threadripper PRO 7955WX 16-Cores 205,8 tok/s this runAMD Ryzen Threadripper PRO 5975WX 32-Cores 103,9 tok/sAMD Ryzen 5 5600X 6-Core Processor 57,1 tok/s

MBby mainboard

8306234152080,003.4326.86410.296Prefill (tok/s)Generation (tok/s)ASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI - 647,6 tok/s Generation, 8.500 tok/s Prefill, TTFT 5.252 ms (3 Laufe)ASUSTeK COMPUTER INC....ASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING - 625,1 tok/s Generation, 7.381 tok/s Prefill, TTFT 5.802 ms (3 Laufe)ASUSTeK COMPUTER INC....Meigao Innovation Technology (Shen Zhen) Co., Ltd DRFXL (MotherBoard Series) - 317,4 tok/s Generation, 4.619 tok/s Prefill, TTFT 10.835 ms (3 Laufe)Meigao Innovation Tec...ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI - 103,9 tok/s Generation, 2.486 tok/s Prefill, TTFT 34.598 ms (5 Laufe)ASUSTeK COMPUTER INC....ASUSTeK COMPUTER INC. PRIME A520M-K - 57,1 tok/s Generation, 1.354 tok/s Prefill, TTFT 5.590 ms (3 Laufe)ASUSTeK COMPUTER INC....ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE - 572,2 tok/s Generation, 8.319 tok/s Prefill, TTFT 9.884 ms (21 Laufe) | DIESER LAUF★ ASUSTeK COMPUTER INC....
ASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI 647,6 tok/sASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING 625,1 tok/s★ ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE 572,2 tok/s this runMeigao Innovation Technology (Shen Zhen) Co., Ltd DRFXL (MotherBoard Series) 317,4 tok/sASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI 103,9 tok/sASUSTeK COMPUTER INC. PRIME A520M-K 57,1 tok/s

ENGby engine

8306234152080,002.8555.7108.565Prefill (tok/s)Generation (tok/s)unbekannt - 57,1 tok/s Generation, 1.354 tok/s Prefill, TTFT 5.590 ms (3 Laufe)unbekanntllama.cpp - 647,6 tok/s Generation, 7.104 tok/s Prefill, TTFT 12.749 ms (35 Laufe) | DIESER LAUF★ llama.cpp
★ llama.cpp 647,6 tok/s this rununbekannt 57,1 tok/s

DRVby driver

7126806486155836.2516.5176.7837.049Prefill (tok/s)Generation (tok/s)unbekannt - 647,6 tok/s Generation, 6.650 tok/s Prefill, TTFT 12.184 ms (38 Laufe)unbekannt
unbekannt 647,6 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 %
🖥️ Acquisition EUR
🔌 Idle 125 W
⚡ TDP 971 W
☁️ External LLM (API)
Electricity0.30 EUR/kWh
Avg power (incl. idle)971 W estimated (TDP)GPU 900 + CPU 46 + Board 25 W full load
Avg cost / hourEUR 0.29
Electricity / 1M tokensEUR 2.46
Token / kWh122.16K
Acquisition (system)EUR 9,674 full priceGPU EUR 4,200 · CPU EUR 1,399 · Board EUR 1,299 · RAM EUR 2,576 · PSU EUR 200
Electricity (2 years)
TCO (2 years)EUR 14,778
Output tokens (2 years)2.08B
☁️ 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 (125 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

Devstral-Small-25073x AMD Radeon AI PRO R9700Devstral-Small-2507NVIDIA GeForce RTX 5090Devstral-Small-2507NVIDIA RTX PRO 6000 Blackwell Workstation EditionDevstral-Small-25073x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition
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.