Created bymario-alka.dePowered bygodcore.denoob2claw.detricoma.de
DEEN
Sign in Sign up
Beta
Contributed byMario AlkaZ.ai (Zhipu)

GLM-4.5-Air

Performance benchmark · measured on 27.07.2026 12:48

Benchmark-IDrun-20260727-125308-0c484e
Timebench 3 - Kombi (Prefill + Generation)MoE106BRuntime: llama.cppQuantisierung: Q4_K_M
Generation9,87tok/s
Prefill112,05tok/s
Time to First Token19.038,00ms
Total duration245,66s
Concurrency1parallel
Ranking in the field
This GPUAll GPUs
107of 144 systems

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

This run is better than 26 % of all comparable systems.
Generation 9,9 tok/s
-87 % vs Ø 74,3
Prefill 112,1 tok/s
-96 % vs Ø 2.824,4
Time to First Token 19.038 ms
+51 % vs Ø 12.636
Distribution in the field0 – 405 tok/s
Ø 74 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)

NVIDIA GeForce RTX 5070 Ti this runrun-20260727-125308-0c484e
9,9 tok/s
NVIDIA GeForce RTX 5090run-20260723-142059-e9bba2
3,3 tok/s
Keine GPU (CPU-only)run-20260723-055734-adc759
2,1 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: GLM-4.5-Air

Configuration

benchmark-konfiguration — run-20260727-125308-0c484e
# LLM-Benchmark Konfiguration # Modell : GLM-4.5-Air # Engine : llama.cpp # Run-ID : run-20260727-125308-0c484e # 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--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 0 \ -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.0
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

13510167,433,70,009651.9302.895Prefill (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 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 GeForce RTX 5070 Ti - 9,9 tok/s Generation, 109 tok/s Prefill, TTFT 59.573 ms (3 Laufe) | DIESER LAUF★ NVIDIA GeForce RTX 50...
AMD Radeon AI PRO R9700 104,1 tok/s★ NVIDIA GeForce RTX 5070 Ti 9,9 tok/s this runNVIDIA GeForce RTX 5090 6,2 tok/sCPU-only 2,1 tok/s

CPUby processor

13510167,433,70,009651.9302.895Prefill (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 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 5975WX 32-Cores - 9,9 tok/s Generation, 109 tok/s Prefill, TTFT 59.573 ms (3 Laufe) | DIESER LAUF★ AMD Ryzen Threadrippe...
AMD Ryzen Threadripper PRO 7955WX 16-Cores 104,1 tok/s★ AMD Ryzen Threadripper PRO 5975WX 32-Cores 9,9 tok/s this runAMD 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

13510167,433,70,009651.9302.895Prefill (tok/s)Generation (tok/s)ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE - 104,1 tok/s Generation, 2.337 tok/s Prefill, TTFT 6.590 ms (2 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 WRX80E-SAGE SE WIFI - 9,9 tok/s Generation, 109 tok/s Prefill, TTFT 59.573 ms (3 Laufe) | DIESER LAUF★ ASUSTeK COMPUTER INC....
ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE 104,1 tok/s★ ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI 9,9 tok/s this runASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING 6,2 tok/sDell Inc. PowerEdge R820 2,1 tok/s

ENGby engine

13410167,033,50,0132417702986Prefill (tok/s)Generation (tok/s)vLLM - 6,2 tok/s Generation, 282 tok/s Prefill, TTFT 23.682 ms (2 Laufe)vLLMllama.cpp - 104,1 tok/s Generation, 836 tok/s Prefill, TTFT 51.644 ms (6 Laufe) | DIESER LAUF★ llama.cpp
★ llama.cpp 104,1 tok/s this runvLLM 6,2 tok/s

DRVby driver

11410910498,993,7656684712740Prefill (tok/s)Generation (tok/s)unbekannt - 104,1 tok/s Generation, 698 tok/s Prefill, TTFT 44.653 ms (8 Laufe)unbekannt
unbekannt 104,1 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 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 0.084
Token / kWh3.55M
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)622.52M
☁️ 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 10 tok/sNVIDIA GeForce RTX 5090 3 tok/sKeine GPU (CPU-only) 2 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.