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

Mistral-Medium-3.5-128B

Performance benchmark · measured on 06.08.2026 10:29

Benchmark-IDrun-20260806-115739-db6ea8
Timebench 3 - Kombi (Prefill + Generation)Dense128BRuntime: llama.cppQuantisierung: Q4_K_M
Generation1,33tok/s
Prefill9,58tok/s
Time to First Token222.220,50ms
Total duration1.200,00s
Concurrency1parallel
Ranking in the field
173of 176 systems

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

This run is better than 2 % of all comparable systems.
Generation 1,3 tok/s
-95 % vs Ø 28,6
Prefill 9,6 tok/s
-99 % vs Ø 1.232,7
Time to First Token 222.221 ms
+563 % vs Ø 33.504
Distribution in the field1 – 140 tok/s
Ø 29 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 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: Mistral-Medium-3.5-128B

Configuration

benchmark-konfiguration — run-20260806-115739-db6ea8
# LLM-Benchmark Konfiguration # Modell : Mistral-Medium-3.5-128B # Engine : llama.cpp # Run-ID : run-20260806-115739-db6ea8 # GPU : 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--unsloth--Mistral-Medium-3.5-128B-GGUF/snapshots/c8f5b1477e1b22cd2d819157d450f001f7047298/Q4_K_M/Mistral-Medium-3.5-128B-Q4_K_M-00001-of-00003.gguf \ --alias Mistral-Medium-3.5-128B \ --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.Mistral-Medium-3.5-128B
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--unsloth--Mistral-Medium-3.5-128B-GGUF/snapshots/c8f5b1477e1b22cd2d819157d450f001f7047298/Q4_K_M/Mistral-Medium-3.5-128B-Q4_K_M-00001-of-00003.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
Model comparison

Mistral-Medium-3.5-128B 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

18413891,845,90,006961.3922.088Prefill (tok/s)Generation (tok/s)NVIDIA RTX PRO 6000 Blackwell Workstation Edition - 141,6 tok/s Generation, 1.700 tok/s Prefill, TTFT 31.951 ms (3 Laufe)NVIDIA RTX PRO 6000 B...NVIDIA GeForce RTX 5070 Ti - 4,2 tok/s Generation, 131 tok/s Prefill, TTFT 53.481 ms (3 Laufe)NVIDIA GeForce RTX 50...NVIDIA GeForce RTX 3090 Ti - 2,8 tok/s Generation, 116 tok/s Prefill, TTFT 59.662 ms (3 Laufe)NVIDIA GeForce RTX 30...NVIDIA GeForce RTX 5090 - 1,9 tok/s Generation, 113 tok/s Prefill, TTFT 72.453 ms (5 Laufe)NVIDIA GeForce RTX 50...AMD Radeon AI PRO R9700 - 21,2 tok/s Generation, 415 tok/s Prefill, TTFT 141.899 ms (5 Laufe) | DIESER LAUF★ AMD Radeon AI PRO R97...
NVIDIA RTX PRO 6000 Blackwell Workstation Edition 141,6 tok/s★ AMD Radeon AI PRO R9700 21,2 tok/s this runNVIDIA GeForce RTX 5070 Ti 4,2 tok/sNVIDIA GeForce RTX 3090 Ti 2,8 tok/sNVIDIA GeForce RTX 5090 1,9 tok/s

CPUby processor

18413891,845,90,006961.3922.088Prefill (tok/s)Generation (tok/s)AMD Ryzen 9 9950X 16-Core Processor - 141,6 tok/s Generation, 1.700 tok/s Prefill, TTFT 31.951 ms (3 Laufe)AMD Ryzen 9 9950X 16-...AMD Ryzen Threadripper PRO 5975WX 32-Cores - 4,2 tok/s Generation, 131 tok/s Prefill, TTFT 53.481 ms (3 Laufe)AMD Ryzen Threadrippe...AMD Ryzen 9 8945HX with Radeon Graphics - 2,8 tok/s Generation, 116 tok/s Prefill, TTFT 59.662 ms (3 Laufe)AMD Ryzen 9 8945HX wi...AMD Ryzen 7 5800X3D 8-Core Processor - 1,9 tok/s Generation, 113 tok/s Prefill, TTFT 72.453 ms (5 Laufe)AMD Ryzen 7 5800X3D 8...AMD Ryzen Threadripper PRO 7955WX 16-Cores - 21,2 tok/s Generation, 415 tok/s Prefill, TTFT 141.899 ms (5 Laufe) | DIESER LAUF★ AMD Ryzen Threadrippe...
AMD Ryzen 9 9950X 16-Core Processor 141,6 tok/s★ AMD Ryzen Threadripper PRO 7955WX 16-Cores 21,2 tok/s this runAMD Ryzen Threadripper PRO 5975WX 32-Cores 4,2 tok/sAMD Ryzen 9 8945HX with Radeon Graphics 2,8 tok/sAMD Ryzen 7 5800X3D 8-Core Processor 1,9 tok/s

MBby mainboard

18413891,845,90,006961.3922.088Prefill (tok/s)Generation (tok/s)ASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI - 141,6 tok/s Generation, 1.700 tok/s Prefill, TTFT 31.951 ms (3 Laufe)ASUSTeK COMPUTER INC....ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI - 4,2 tok/s Generation, 131 tok/s Prefill, TTFT 53.481 ms (3 Laufe)ASUSTeK COMPUTER INC....Meigao Innovation Technology (Shen Zhen) Co., Ltd DRFXL (MotherBoard Series) - 2,8 tok/s Generation, 116 tok/s Prefill, TTFT 59.662 ms (3 Laufe)Meigao Innovation Tec...ASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING - 1,9 tok/s Generation, 113 tok/s Prefill, TTFT 72.453 ms (5 Laufe)ASUSTeK COMPUTER INC....ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE - 21,2 tok/s Generation, 415 tok/s Prefill, TTFT 141.899 ms (5 Laufe) | DIESER LAUF★ ASUSTeK COMPUTER INC....
ASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI 141,6 tok/s★ ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE 21,2 tok/s this runASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI 4,2 tok/sMeigao Innovation Technology (Shen Zhen) Co., Ltd DRFXL (MotherBoard Series) 2,8 tok/sASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING 1,9 tok/s

ENGby engine

156149142134127420438456473Prefill (tok/s)Generation (tok/s)llama.cpp - 141,6 tok/s Generation, 447 tok/s Prefill, TTFT 79.318 ms (19 Laufe) | DIESER LAUF★ llama.cpp
★ llama.cpp 141,6 tok/s this run

DRVby driver

156149142134127420438456473Prefill (tok/s)Generation (tok/s)unbekannt - 141,6 tok/s Generation, 447 tok/s Prefill, TTFT 79.318 ms (19 Laufe)unbekannt
unbekannt 141,6 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 85 W
⚡ TDP 371 W
☁️ External LLM (API)
Electricity0.30 EUR/kWh
Avg power (incl. idle)371 W estimated (TDP)GPU 300 + CPU 46 + Board 25 W full load
Avg cost / hourEUR 0.11
Electricity / 1M tokensEUR 23.25
Token / kWh12.91K
Acquisition (system)EUR 6,824 full priceGPU EUR 1,400 · CPU EUR 1,399 · Board EUR 1,299 · RAM EUR 2,576 · PSU EUR 150
Electricity (2 years)
TCO (2 years)EUR 8,774
Output tokens (2 years)83.89M
☁️ 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 (85 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-Medium-3.5-128BAMD Radeon AI PRO R9700Mistral-Medium-3.5-128BNVIDIA RTX PRO 6000 Blackwell Workstation EditionMistral-Medium-3.5-128BNVIDIA GeForce RTX 5070 TiMistral-Medium-3.5-128BAMD Radeon AI PRO R9700
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.