Created bymario-alka.dePowered bygodcore.denoob2claw.detricoma.de
Contributed byMario AlkaZ.ai (Zhipu)

GLM-4.5-Air

Performance benchmark · measured on 27.07.2026 19:21

Benchmark-IDrun-20260727-193100-9a2d59
Timebench 3 - Kombi (Prefill + Generation)MoE106BRuntime: llama.cppQuantisierung: Q4_K_M
Generation615,32tok/s
Prefill5.004,90tok/s
Time to First Token17.981,50ms
Total duration106,29s
Concurrency10parallel
Ranking in the field
38of 148 systems

Performance benchmark · Primary metric: Generation-Speed (tok/s) · 10× concurrent

This run is better than 75 % of all comparable systems.
Generation 615,3 tok/s
+58 % vs Ø 390,6
Prefill 5.004,9 tok/s
-32 % vs Ø 7.373,8
Time to First Token 17.982 ms
-54 % vs Ø 39.308
Distribution in the field0 – 2.414 tok/s
Ø 391 Median Dieser Lauf

Wie schlägt sich dieser Benchmark mit anderen Modellen?

How does this benchmark compare on other GPUs?

Same model on different hardware · 10× concurrent · Generation (tok/s)

Hardware

GPU: 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · 96 GB VRAM
CPU: AMD Ryzen Threadripper PRO 9965WX 24-Cores
RAM: 125 GB
Mainboard: ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE

Setup

Runtime: llama.cpp
Quantization: Q4_K_M
Model: GLM-4.5-Air

Configuration

benchmark-konfiguration — run-20260727-193100-9a2d59
# LLM-Benchmark Konfiguration # Modell : GLM-4.5-Air # Engine : llama.cpp # Run-ID : run-20260727-193100-9a2d59 # GPU : 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition # CPU : AMD Ryzen Threadripper PRO 9965WX 24-Cores # RAM : 125 GB bench@llm-benchmark:~$ /home/godcore/llama.cpp/build/bin/llama-server \ -m /home/godcore/.cache/huggingface/hub/models--unsloth--GLM-4.5-Air-GGUF/snapshots/506d64aa8c5cfe9dbbf00bc7a15739438f83204d/Q4_K_M/GLM-4.5-Air-Q4_K_M-00001-of-00002.gguf \ --alias GLM-4.5-Air \ --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.GLM-4.5-Air
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--GLM-4.5-Air-GGUF/snapshots/506d64aa8c5cfe9dbbf00bc7a15739438f83204d/Q4_K_M/GLM-4.5-Air-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.16384
np4

All benchmarks of this model To leaderboard

Model comparison

GLM-4.5-Air 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

7996004002000,001.8063.6115.417Prefill (tok/s)Generation (tok/s)AMD Radeon AI PRO R9700 - 104,1 tok/s Generation, 2.337 tok/s Prefill, TTFT 6.590 ms (2 Laufe)AMD Radeon AI PRO R97...NVIDIA GeForce RTX 3090 Ti - 20,8 tok/s Generation, 137 tok/s Prefill, TTFT 156.298 ms (3 Laufe)NVIDIA GeForce RTX 30...NVIDIA GeForce RTX 5070 Ti - 9,9 tok/s Generation, 109 tok/s Prefill, TTFT 59.573 ms (3 Laufe)NVIDIA GeForce RTX 50...NVIDIA GeForce RTX 5090 - 6,2 tok/s Generation, 282 tok/s Prefill, TTFT 23.682 ms (2 Laufe)NVIDIA GeForce RTX 50...CPU-only - 2,1 tok/s Generation, 18 tok/s Prefill, TTFT 117.963 ms (1 Lauf)CPU-onlyNVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition - 615,3 tok/s Generation, 4.371 tok/s Prefill, TTFT 8.072 ms (3 Laufe) | DIESER LAUF★ NVIDIA RTX PRO 6000 B...
★ NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 615,3 tok/s this runAMD Radeon AI PRO R9700 104,1 tok/sNVIDIA GeForce RTX 3090 Ti 20,8 tok/sNVIDIA GeForce RTX 5070 Ti 9,9 tok/sNVIDIA GeForce RTX 5090 6,2 tok/sCPU-only 2,1 tok/s

CPUby processor

7996004002000,001.8063.6115.417Prefill (tok/s)Generation (tok/s)AMD Ryzen Threadripper PRO 7955WX 16-Cores - 104,1 tok/s Generation, 2.337 tok/s Prefill, TTFT 6.590 ms (2 Laufe)AMD Ryzen Threadrippe...AMD Ryzen 9 8945HX with Radeon Graphics - 20,8 tok/s Generation, 137 tok/s Prefill, TTFT 156.298 ms (3 Laufe)AMD Ryzen 9 8945HX wi...AMD Ryzen Threadripper PRO 5975WX 32-Cores - 9,9 tok/s Generation, 109 tok/s Prefill, TTFT 59.573 ms (3 Laufe)AMD Ryzen Threadrippe...AMD Ryzen 7 5800X3D 8-Core Processor - 6,2 tok/s Generation, 282 tok/s Prefill, TTFT 23.682 ms (2 Laufe)AMD Ryzen 7 5800X3D 8...Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz - 2,1 tok/s Generation, 18 tok/s Prefill, TTFT 117.963 ms (1 Lauf)Intel(R) Xeon(R) CPU ...AMD Ryzen Threadripper PRO 9965WX 24-Cores - 615,3 tok/s Generation, 4.371 tok/s Prefill, TTFT 8.072 ms (3 Laufe) | DIESER LAUF★ AMD Ryzen Threadrippe...
★ AMD Ryzen Threadripper PRO 9965WX 24-Cores 615,3 tok/s this runAMD Ryzen Threadripper PRO 7955WX 16-Cores 104,1 tok/sAMD Ryzen 9 8945HX with Radeon Graphics 20,8 tok/sAMD Ryzen Threadripper PRO 5975WX 32-Cores 9,9 tok/sAMD Ryzen 7 5800X3D 8-Core Processor 6,2 tok/sIntel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz 2,1 tok/s

MBby mainboard

7996004002000,001.4692.9394.408Prefill (tok/s)Generation (tok/s)Meigao Innovation Technology (Shen Zhen) Co., Ltd DRFXL (MotherBoard Series) - 20,8 tok/s Generation, 137 tok/s Prefill, TTFT 156.298 ms (3 Laufe)Meigao Innovation Tec...ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI - 9,9 tok/s Generation, 109 tok/s Prefill, TTFT 59.573 ms (3 Laufe)ASUSTeK COMPUTER INC....ASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING - 6,2 tok/s Generation, 282 tok/s Prefill, TTFT 23.682 ms (2 Laufe)ASUSTeK COMPUTER INC....Dell Inc. PowerEdge R820 - 2,1 tok/s Generation, 18 tok/s Prefill, TTFT 117.963 ms (1 Lauf)Dell Inc. PowerEdge R...ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE - 615,3 tok/s Generation, 3.557 tok/s Prefill, TTFT 7.479 ms (5 Laufe) | DIESER LAUF★ ASUSTeK COMPUTER INC....
★ ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE 615,3 tok/s this runMeigao Innovation Technology (Shen Zhen) Co., Ltd DRFXL (MotherBoard Series) 20,8 tok/sASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI 9,9 tok/sASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING 6,2 tok/sDell Inc. PowerEdge R820 2,1 tok/s

ENGby engine

7995993992000,006221.2431.865Prefill (tok/s)Generation (tok/s)vLLM - 6,2 tok/s Generation, 282 tok/s Prefill, TTFT 23.682 ms (2 Laufe)vLLMllama.cpp - 615,3 tok/s Generation, 1.545 tok/s Prefill, TTFT 66.914 ms (12 Laufe) | DIESER LAUF★ llama.cpp
★ llama.cpp 615,3 tok/s this runvLLM 6,2 tok/s

DRVby driver

6776466155855541.2831.3371.3921.447Prefill (tok/s)Generation (tok/s)unbekannt - 615,3 tok/s Generation, 1.365 tok/s Prefill, TTFT 60.738 ms (14 Laufe)unbekannt
unbekannt 615,3 tok/s
💰 Economics

Economics of this run

Operating cost, TCO and comparison with the next-best runs of the same model at identical concurrency (10× 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 165 W
⚡ TDP 983 W
☁️ External LLM (API)
Electricity0.30 EUR/kWh
Avg power (incl. idle)983 W estimated (TDP)GPU 900 + CPU 57 + Board 25 W full load
Avg cost / hourEUR 0.29
Electricity / 1M tokensEUR 0.13
Token / kWh2.25M
Acquisition (system)EUR 45,748 full priceGPU EUR 39,000 · CPU EUR 3,499 · Board EUR 1,299 · RAM EUR 1,750 · PSU EUR 200
Electricity (2 years)
TCO (2 years)EUR 50,912
Output tokens (2 years)38.81B
☁️ 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 (165 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

GLM-4.5-Air3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionGLM-4.5-Air3x AMD Radeon AI PRO R9700GLM-4.5-AirNVIDIA GeForce RTX 3090 TiGLM-4.5-AirNVIDIA GeForce RTX 5070 Ti
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.