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

Devstral-Small-2507

Performance benchmark · measured on 27.07.2026 10:57

Benchmark-IDrun-20260727-113142-d5f9a5
Timebench 3 - Kombi (Prefill + Generation)Dense24BRuntime: llama.cppQuantisierung: Q4_K_M
Generation57,59tok/s
Prefill2.616,63tok/s
Time to First Token21.157,50ms
Total duration223,48s
Concurrency5parallel
Ranking in the field
This GPUAll GPUs
9of 20 systems

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

This run is better than 58 % of all comparable systems.
Generation 57,6 tok/s
-79 % vs Ø 274,3
Prefill 2.616,6 tok/s
-39 % vs Ø 4.289,7
Time to First Token 21.158 ms
-16 % vs Ø 25.319
Distribution in the field4 – 974 tok/s
Ø 274 Median Dieser Lauf

Wie schlägt sich dieser Benchmark mit anderen Modellen?

How does this benchmark compare on other GPUs?

Same model on different hardware · 5× concurrent · Generation (tok/s)

NVIDIA GeForce RTX 3090 Tirun-20260727-155936-392c08
173,4 tok/s
NVIDIA GeForce RTX 5070 Ti this runrun-20260727-113142-d5f9a5
57,6 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: Q4_K_M
Model: Devstral-Small-2507

Configuration

benchmark-konfiguration — run-20260727-113142-d5f9a5
# LLM-Benchmark Konfiguration # Modell : Devstral-Small-2507 # Engine : llama.cpp # Run-ID : run-20260727-113142-d5f9a5 # 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--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 30 \ -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.30
Kontext?Groesse des Kontextfensters in Token. 0 = der beim Training verwendete Kontext des Modells.16384
np4

All benchmarks of this model To leaderboard

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

39230121112029,52.1153.1554.1955.235Prefill (tok/s)Generation (tok/s)NVIDIA GeForce RTX 3090 Ti - 317,4 tok/s Generation, 4.619 tok/s Prefill, TTFT 10.835 ms (3 Laufe)NVIDIA GeForce RTX 30...NVIDIA GeForce RTX 5070 Ti - 103,9 tok/s Generation, 2.732 tok/s Prefill, TTFT 42.889 ms (2 Laufe) | DIESER LAUF★ NVIDIA GeForce RTX 50...
NVIDIA GeForce RTX 3090 Ti 317,4 tok/s★ NVIDIA GeForce RTX 5070 Ti 103,9 tok/s this run

CPUby processor

39230121112029,52.1153.1554.1955.235Prefill (tok/s)Generation (tok/s)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, 2.732 tok/s Prefill, TTFT 42.889 ms (2 Laufe) | DIESER LAUF★ AMD Ryzen Threadrippe...
AMD Ryzen 9 8945HX with Radeon Graphics 317,4 tok/s★ AMD Ryzen Threadripper PRO 5975WX 32-Cores 103,9 tok/s this run

MBby mainboard

39230121112029,52.1153.1554.1955.235Prefill (tok/s)Generation (tok/s)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, 2.732 tok/s Prefill, TTFT 42.889 ms (2 Laufe) | DIESER LAUF★ ASUSTeK COMPUTER INC....
Meigao Innovation Technology (Shen Zhen) Co., Ltd DRFXL (MotherBoard Series) 317,4 tok/s★ ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI 103,9 tok/s this run

ENGby engine

3493333173022863.6323.7873.9414.096Prefill (tok/s)Generation (tok/s)llama.cpp - 317,4 tok/s Generation, 3.864 tok/s Prefill, TTFT 23.656 ms (5 Laufe) | DIESER LAUF★ llama.cpp
★ llama.cpp 317,4 tok/s this run

DRVby driver

3493333173022863.6323.7873.9414.096Prefill (tok/s)Generation (tok/s)unbekannt - 317,4 tok/s Generation, 3.864 tok/s Prefill, TTFT 23.656 ms (5 Laufe)unbekannt
unbekannt 317,4 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 10 W
⚡ TDP 10 W
☁️ External LLM (API)
Electricity0.30 EUR/kWh
Avg power (incl. idle)10 W missingBoard 10 W full load
Avg cost / hourEUR 0.0030
Electricity / 1M tokensEUR 0.014
Token / kWh20.73M
Acquisition (system)EUR 2,096 missingRAM EUR 1,976 · PSU EUR 120
Electricity (2 years)–
TCO (2 years)EUR 2,149
Output tokens (2 years)3.63B
☁️ 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 (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

NVIDIA GeForce RTX 5070 Ti · this run 58 tok/sNVIDIA GeForce RTX 3090 Ti 173 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.