Contributed byMario AlkaMistral AI Devstral-2-123B-Instruct-2512
Performance benchmark · measured on 21.07.2026 16:23
Benchmark-ID
run-20260722-165907-12f95aDense123BRuntime: godclawQuantisierung: Q4_K_M
Generation6,50tok/s
Prefill323,20tok/s
Time to First Token6.557,00ms
Total duration138,83s
Concurrency1parallel
Ranking in the field
372of 455 systems
Performance benchmark · Primary metric: Generation-Speed (tok/s) · 1× concurrent
This run is better than 18 % of all comparable systems.
Generation
6,5 tok/s
-82 % vs Ø 35,3
Prefill
323,2 tok/s
-84 % vs Ø 1.966,4
Time to First Token
6.557 ms
-82 % vs Ø 35.848
Distribution in the field1 – 148 tok/s
Wie schlägt sich dieser Benchmark mit anderen Modellen?
gpt-oss-20b3× AMD Radeon AI PRO R9700 · run-20260722-165909-85f64f
147,8 tok/s
gpt-oss-20b3× AMD Radeon AI PRO R9700 · run-20260722-165908-d95290
147,8 tok/s
gpt-oss-20b3× AMD Radeon AI PRO R9700 · run-20260722-165909-637af7
143,9 tok/s
gpt-oss-20b3× AMD Radeon AI PRO R9700 · run-20260722-165908-95273d
143,9 tok/s
Nemotron-3-Nano-4B3× AMD Radeon AI PRO R9700 · run-20260805-053357-112090
139,8 tok/s
gpt-oss-20b3× AMD Radeon AI PRO R9700 · run-20260722-165909-65d35f
137,7 tok/s
gpt-oss-20b3× AMD Radeon AI PRO R9700 · run-20260722-165908-ff206d
137,7 tok/s
Nemotron-3-Nano-4B3× AMD Radeon AI PRO R9700 · run-20260805-053357-ed67ec
136,2 tok/s
Nemotron-3-Nano-4B3× AMD Radeon AI PRO R9700 · run-20260805-053357-16d611
129,5 tok/s
Nemotron-3-Nano-30B-A3B4× AMD Radeon AI PRO R9700 · run-20260817-111922-dd07f5
125,7 tok/s
Nemotron-3.5-Lightning-30B-A3B4× AMD Radeon AI PRO R9700 · run-20260815-060242-025c3d
121,3 tok/s
Nemotron-3.5-Lightning-30B-A3B4× AMD Radeon AI PRO R9700 · run-20260815-060242-dadb7a
113,6 tok/s
Nemotron-3.5-Lightning-30B-A3B4× AMD Radeon AI PRO R9700 · run-20260815-060243-6a7849
108,1 tok/s
Nemotron-Cascade-2-30B-A3B3× AMD Radeon AI PRO R9700 · run-20260722-181156-a273f2
107,9 tok/s
Devstral-2-123B-Instruct-2512 this run3× AMD Radeon AI PRO R9700 · run-20260722-165907-12f95a
6,5 tok/s
How does this benchmark compare on other GPUs?
Same model on different hardware · 1× concurrent · Generation (tok/s)
NVIDIA RTX PRO 6000 Blackwell Workstation Editionrun-20260729-060804-fb778c
19,7 tok/s
3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Editionrun-20260806-115740-8815e2
18,6 tok/s
3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Editionrun-20260806-115740-a2fcbb
18,5 tok/s
3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Editionrun-20260806-115739-1dc0ca
15,8 tok/s
4× AMD Radeon AI PRO R9700run-20260813-073605-793dd1
7,2 tok/s
4× AMD Radeon AI PRO R9700run-20260817-111923-11c9d2
7,0 tok/s
4× AMD Radeon AI PRO R9700run-20260817-181637-f06761
6,9 tok/s
4× AMD Radeon AI PRO R9700run-20260817-111923-89bc23
6,8 tok/s
3× AMD Radeon AI PRO R9700 this runrun-20260722-165907-12f95a
6,5 tok/s
3× AMD Radeon AI PRO R9700run-20260722-165908-f3e478
6,5 tok/s
NVIDIA GeForce RTX 5070 Tirun-20260729-122848-c1df2a
1,7 tok/s
3× AMD Radeon AI PRO R9700run-20260806-094442-e653f9
1,4 tok/s
3× AMD Radeon AI PRO R9700run-20260809-101923-b14eae
1,4 tok/s
3× AMD Radeon AI PRO R9700run-20260805-053415-6cd593
1,4 tok/s
Hardware
GPU: 3x AMD Radeon AI PRO R9700 · 32 GB VRAM
CPU: 32x AMD Ryzen Threadripper PRO 7955WX 16-Cores
RAM: 184 GB
Mainboard: ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE
Setup
Runtime: godclaw
Quantization: Q4_K_M
Operating system: Ubuntu 26.04 LTS (Kernel 7.0.0-27-generic)
Driver: AMD 7.0.0-27-generic
Model: Devstral-2-123B-Instruct-2512
Anmerkung
llama.cpp . 3 GPU . GGUF (unsloth/Devstral-2-123B-Instruct-2512-GGUF)
Configuration
# LLM-Benchmark Konfiguration
# Modell : Devstral-2-123B-Instruct-2512
# Run-ID : run-20260722-165907-12f95a
# GPU : 3x AMD Radeon AI PRO R9700
# CPU : 32x AMD Ryzen Threadripper PRO 7955WX 16-Cores
# RAM : 184 GB
bench@llm-benchmark:~$ cat benchmark.conf
Konfigurationspfad /root/.cache/huggingface/hub/models--unsloth--Devstral-2-123B-Instruct-2512-GGUF/snapshots/1f2bfbe35f7f9071d9b318374bf5eeffefab4459/Q4_K_M/Devstral-2-123B-Instruct-2512-Q4_K_M-00001-of-00002.gguf
Engine llamacpp
Modellalias Devstral-2-123B-Instruct-2512
Kontextlaenge 8192
GPU-Layer 999
Split-Mode layer
Host 0.0.0.0
Port 8000
| 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-2-123B-Instruct-2512 |
| Kontextlaenge?Maximale Anzahl Tokens (Eingabe + erzeugte Ausgabe zusammen), die das Modell pro Anfrage verarbeiten kann. | 8192 |
| Modellpfad?Pfad zur GGUF-Modelldatei, die geladen und ausgeliefert wird. | /root/.cache/huggingface/hub/models--unsloth--Devstral-2-123B-Instruct-2512-GGUF/snapshots/1f2bfbe35f7f9071d9b318374bf5eeffefab4459/Q4_K_M/Devstral-2-123B-Instruct-2512-Q4_K_M-00001-of-00002.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. | 8192 |
| Alias?Anzeigename des Modells nach aussen (served model name), unabhaengig vom Dateinamen. | Devstral-2-123B-Instruct-2512 |
| Split-Mode?Verteilung ueber mehrere GPUs: none (nur eine GPU), layer (Layer aufteilen) oder row (Tensoren zeilenweise). | layer |
| Host?Netzwerk-Interface, an das der HTTP-Server bindet, z.B. 0.0.0.0 fuer alle Interfaces. | 0.0.0.0 |
| Port?TCP-Port des HTTP-Servers. | 8000 |
Anzeige
Videoreihe und Benchmarkauswertung zur AMD R9700
Model comparison
Devstral-2-123B-Instruct-2512 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
CPUby processor
AMD Ryzen 9 9950X 16-Core Processor 143,1 tok/sAMD Ryzen Threadripper PRO 9965WX 24-Cores 123,5 tok/s★ AMD Ryzen Threadripper PRO 7955WX 16-Cores 50,0 tok/s this runAMD Ryzen Threadripper PRO 5975WX 32-Cores 4,5 tok/sAMD Ryzen 9 8945HX with Radeon Graphics 2,9 tok/sAMD Ryzen 7 5800X3D 8-Core Processor 2,1 tok/s
MBby mainboard
ASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI 143,1 tok/s★ ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE 123,5 tok/s this runASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI 4,5 tok/sMeigao Innovation Technology (Shen Zhen) Co., Ltd DRFXL (MotherBoard Series) 2,9 tok/sASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING 2,1 tok/s
DRVby driver
unbekannt 143,1 tok/s★ AMD 7.0.0-27-generic 6,5 tok/s this run
💰 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 12.45
Token / kWh24.10K
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)409.97M
☁️ 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-2-123B-Instruct-25123x AMD Radeon AI PRO R9700 | Devstral-2-123B-Instruct-2512NVIDIA RTX PRO 6000 Blackwell Workstation Edition | Devstral-2-123B-Instruct-25123x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition | Devstral-2-123B-Instruct-25123x 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) | – | – | – | – |
3× AMD Radeon AI PRO R9700 · this run 7 tok/sNVIDIA RTX PRO 6000 Blackwell Workstation Edition 20 tok/s3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 19 tok/s3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 19 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.