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

GLM-4.5-Air

Performance benchmark · measured on 23.07.2026 13:46

Benchmark-IDrun-20260723-142100-c471d1
Timebench 3 - Kombi (Prefill + Generation)MoE106BRuntime: vLLMQuantisierung: AWQ
For context: Teile des Modells wurden per --cpu-offload-gb=40 GB in den System-RAM ausgelagert – RAM wird als erweiterter VRAM genutzt, was den Durchsatz senken kann.
Generation6,20tok/s
Prefill382,08tok/s
Time to First Token35.624,50ms
Total duration600,00s
Concurrency5parallel
Ranking in the field
1170of 1224 systems

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

This run is better than 4 % of all comparable systems.
Generation 6,2 tok/s
-98 % vs Ø 261,0
Prefill 382,1 tok/s
-93 % vs Ø 5.346,4
Time to First Token 35.625 ms
+19 % vs Ø 29.991
Distribution in the field0 – 1.349 tok/s
Ø 261 Median Dieser Lauf

Wie schlägt sich dieser Benchmark mit anderen Modellen?

gemma-4-E2B-itNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260727-181606-0adf6d
1.349,3 tok/s
gemma-4-E2B-itNVIDIA GeForce RTX 5090 · run-20260728-184455-5b4937
1.301,9 tok/s
gemma-4-E2B-it3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-184456-4111a9
1.195,7 tok/s
Nemotron-3-Nano-4BNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260727-181607-30d864
1.188,7 tok/s
Nemotron-3-Nano-4BNVIDIA GeForce RTX 5090 · run-20260728-194135-5432cd
1.164,8 tok/s
gpt-oss-20bNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260728-140954-9e81f9
1.136,3 tok/s
gpt-oss-20bNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260730-035052-09627f
1.135,0 tok/s
gpt-oss-20bNVIDIA GeForce RTX 5090 · run-20260729-032121-058a31
1.113,5 tok/s
Nemotron-3-Nano-4B3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-194136-836a91
1.090,6 tok/s
Nemotron-3-Nano-4B3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260727-181606-8b381e
1.077,4 tok/s
Nemotron-3-Nano-4B3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-194136-b8a818
1.071,0 tok/s
Nemotron-3-Nano-4B3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-194136-038e92
1.051,1 tok/s
gpt-oss-20b3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260729-032121-ffb18a
1.015,5 tok/s
Nemotron-3-Nano-30B-A3BNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260729-032121-305ad6
1.007,8 tok/s
GLM-4.5-Air this runNVIDIA GeForce RTX 5090 · run-20260723-142100-c471d1
6,2 tok/s

How does this benchmark compare on other GPUs?

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

Hardware

GPU: NVIDIA GeForce RTX 5090 · 32 GB VRAM
CPU: AMD Ryzen 7 5800X3D 8-Core Processor
RAM: 126 GB
Mainboard: ASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING

Setup

Runtime: vLLM
Quantization: AWQ
Model: GLM-4.5-Air

Configuration

benchmark-konfiguration — run-20260723-142100-c471d1
# LLM-Benchmark Konfiguration # Modell : GLM-4.5-Air # Engine : vLLM # Run-ID : run-20260723-142100-c471d1 # GPU : NVIDIA GeForce RTX 5090 # CPU : AMD Ryzen 7 5800X3D 8-Core Processor # RAM : 126 GB bench@llm-benchmark:~$ /opt/gcs_venv/bin/python3 /opt/gcs_venv/bin/vllm serve cyankiwi/GLM-4.5-Air-AWQ-4bit \ --served-model-name GLM-4.5-Air \ --dtype auto \ --max-model-len 8192 \ --gpu-memory-utilization 0.92 \ --cpu-offload-gb 40 \ --trust-remote-code \ --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.vllm
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.8192
Alias?Anzeigename des Modells nach aussen (served model name), unabhaengig vom Dateinamen.GLM-4.5-Air
Dtype?Zahlenformat der Modellgewichte bei der Berechnung (z.B. auto, float16, bfloat16). 'auto' waehlt automatisch das vom Modell empfohlene Format.auto
Kontext?Groesse des Kontextfensters in Token. 0 = der beim Training verwendete Kontext des Modells.8192
GPU-Speicher?Anteil des GPU-Speichers (0 bis 1), den vLLM belegen darf. 0.92 = 92 %. Hoeher = mehr Platz fuer den KV-Cache (mehr/laengere parallele Anfragen), aber groesseres Risiko fuer 'Out of Memory'.0.92
cpu-offload-gb?Menge an Modellgewichten in GiB, die in den CPU-RAM ausgelagert wird. Ermoeglicht groessere Modelle als der GPU-Speicher fasst, kostet aber Geschwindigkeit.40
Trust-Remote-Code?Erlaubt vLLM, mit dem Modell mitgelieferten Python-Code auszufuehren. Noetig fuer Architekturen, die vLLM nicht von Haus aus kennt. Nur bei vertrauenswuerdigen Modellen aktivieren.aktiv

All benchmarks of this model To leaderboard

Anzeige
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

8606454302150,003.2576.5159.772Prefill (tok/s)Generation (tok/s)NVIDIA RTX PRO 6000 Blackwell Workstation Edition - 661,8 tok/s Generation, 3.117 tok/s Prefill, TTFT 8.401 ms (3 Laufe)NVIDIA RTX PRO 6000 B...NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition - 615,3 tok/s Generation, 3.448 tok/s Prefill, TTFT 9.105 ms (12 Laufe)NVIDIA RTX PRO 6000 B...NVIDIA RTX A6000 - 276,5 tok/s Generation, 7.883 tok/s Prefill, TTFT 1.739 ms (6 Laufe)NVIDIA RTX A6000AMD Radeon AI PRO R9700 - 104,1 tok/s Generation, 1.403 tok/s Prefill, TTFT 67.488 ms (11 Laufe)AMD Radeon AI PRO R97...AMD Radeon PRO W7900 Dual Slot - 99,5 tok/s Generation, 461 tok/s Prefill, TTFT 57.896 ms (9 Laufe)AMD Radeon PRO W7900 ...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 2060 - 2,1 tok/s Generation, 18 tok/s Prefill, TTFT 117.963 ms (1 Lauf)NVIDIA GeForce RTX 20...NVIDIA GeForce RTX 5090 - 6,2 tok/s Generation, 161 tok/s Prefill, TTFT 57.809 ms (5 Laufe) | DIESER LAUF★ NVIDIA GeForce RTX 50...
NVIDIA RTX PRO 6000 Blackwell Workstation Edition 661,8 tok/sNVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 615,3 tok/sNVIDIA RTX A6000 276,5 tok/sAMD Radeon AI PRO R9700 104,1 tok/sAMD Radeon PRO W7900 Dual Slot 99,5 tok/sNVIDIA GeForce RTX 3090 Ti 20,8 tok/sNVIDIA GeForce RTX 5070 Ti 9,9 tok/s★ NVIDIA GeForce RTX 5090 6,2 tok/s this runNVIDIA GeForce RTX 2060 2,1 tok/s

CPUby processor

8606454302150,001.5243.0484.573Prefill (tok/s)Generation (tok/s)AMD Ryzen 9 9950X 16-Core Processor - 661,8 tok/s Generation, 3.117 tok/s Prefill, TTFT 8.401 ms (3 Laufe)AMD Ryzen 9 9950X 16-...AMD Ryzen Threadripper PRO 9965WX 24-Cores - 615,3 tok/s Generation, 3.448 tok/s Prefill, TTFT 9.105 ms (12 Laufe)AMD Ryzen Threadrippe...AMD Ryzen Threadripper PRO 7955WX 16-Cores - 276,5 tok/s Generation, 3.690 tok/s Prefill, TTFT 44.283 ms (17 Laufe)AMD Ryzen Threadrippe...AMD Ryzen Threadripper PRO 5975WX 32-Cores - 99,5 tok/s Generation, 373 tok/s Prefill, TTFT 58.315 ms (12 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...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 7 5800X3D 8-Core Processor - 6,2 tok/s Generation, 161 tok/s Prefill, TTFT 57.809 ms (5 Laufe) | DIESER LAUF★ AMD Ryzen 7 5800X3D 8...
AMD Ryzen 9 9950X 16-Core Processor 661,8 tok/sAMD Ryzen Threadripper PRO 9965WX 24-Cores 615,3 tok/sAMD Ryzen Threadripper PRO 7955WX 16-Cores 276,5 tok/sAMD Ryzen Threadripper PRO 5975WX 32-Cores 99,5 tok/sAMD Ryzen 9 8945HX with Radeon Graphics 20,8 tok/s★ AMD Ryzen 7 5800X3D 8-Core Processor 6,2 tok/s this runIntel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz 2,1 tok/s

MBby mainboard

8606454302150,001.4832.9664.448Prefill (tok/s)Generation (tok/s)ASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI - 661,8 tok/s Generation, 3.117 tok/s Prefill, TTFT 8.401 ms (3 Laufe)ASUSTeK COMPUTER INC....ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE - 615,3 tok/s Generation, 3.590 tok/s Prefill, TTFT 29.727 ms (29 Laufe)ASUSTeK COMPUTER INC....ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI - 99,5 tok/s Generation, 373 tok/s Prefill, TTFT 58.315 ms (12 Laufe)ASUSTeK COMPUTER INC....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...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. ROG STRIX B550-A GAMING - 6,2 tok/s Generation, 161 tok/s Prefill, TTFT 57.809 ms (5 Laufe) | DIESER LAUF★ ASUSTeK COMPUTER INC....
ASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI 661,8 tok/sASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE 615,3 tok/sASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI 99,5 tok/sMeigao Innovation Technology (Shen Zhen) Co., Ltd DRFXL (MotherBoard Series) 20,8 tok/s★ ASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING 6,2 tok/s this runDell Inc. PowerEdge R820 2,1 tok/s

ENGby engine

8546404272130,02652.5304.7957.060Prefill (tok/s)Generation (tok/s)llama.cpp - 661,8 tok/s Generation, 1.425 tok/s Prefill, TTFT 57.166 ms (42 Laufe)llama.cppunbekannt - 32,9 tok/s Generation, 3.110 tok/s Prefill, TTFT 1.893 ms (2 Laufe)unbekanntvLLM - 276,5 tok/s Generation, 5.900 tok/s Prefill, TTFT 6.467 ms (9 Laufe) | DIESER LAUF★ vLLM
llama.cpp 661,8 tok/s★ vLLM 276,5 tok/s this rununbekannt 32,9 tok/s

DRVby driver

8546404272130,01.8672.3972.9273.457Prefill (tok/s)Generation (tok/s)unbekannt - 661,8 tok/s Generation, 2.215 tok/s Prefill, TTFT 48.219 ms (51 Laufe)unbekanntAMD 7.0.0-27-generic - 32,9 tok/s Generation, 3.110 tok/s Prefill, TTFT 1.893 ms (2 Laufe)AMD 7.0.0-27-generic
unbekannt 661,8 tok/sAMD 7.0.0-27-generic 32,9 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 72 W
⚡ TDP 622 W
☁️ External LLM (API)
Electricity0.30 EUR/kWh
Avg power (incl. idle)622 W estimated (TDP)GPU 575 + CPU 35 + Board 12 W full load
Avg cost / hourEUR 0.19
Electricity / 1M tokensEUR 8.35
Token / kWh35.91K
Acquisition (system)EUR 4,986 full priceGPU EUR 3,300 · CPU EUR 349 · Board EUR 149 · RAM EUR 1,008 · PSU EUR 180
Electricity (2 years)
TCO (2 years)EUR 8,253
Output tokens (2 years)391.05M
☁️ 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 (72 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-AirNVIDIA GeForce RTX 5090GLM-4.5-AirNVIDIA RTX PRO 6000 Blackwell Workstation EditionGLM-4.5-Air3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionGLM-4.5-Air3x 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.