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

glm-4.7-flash

Performance benchmark · measured on 29.09.2026 12:17

Benchmark-IDrun-20260929-111253-2b4345
Timebench 3 - Kombi (Prefill + Generation)Runtime: llama.cppQuantisierung: Q4_K_M
Generation151,70tok/s
Prefill5.294,13tok/s
Time to First Token5.864,50ms
Total duration66,11s
Concurrency10parallel
Ranking in the field
This GPUAll GPUs
53of 59 systems

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

This run is better than 10 % of all comparable systems.
Generation 151,7 tok/s
-51 % vs Ø 312,6
Prefill 5.294,1 tok/s
-52 % vs Ø 11.064,5
Time to First Token 5.865 ms
-55 % vs Ø 13.030
Distribution in the field19 – 718 tok/s
Ø 313 Median Dieser Lauf

Wie schlägt sich dieser Benchmark mit anderen Modellen?

Hardware

GPU: 2x AMD Radeon RX 7900 XTX · 24 GB VRAM
CPU: AMD Ryzen Threadripper PRO 3955WX 16-Cores
RAM: 189 GB
Mainboard: ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI

Setup

Runtime: llama.cpp
Quantization: Q4_K_M
Model: glm-4.7-flash

Configuration

benchmark-konfiguration — run-20260929-111253-2b4345
# LLM-Benchmark Konfiguration # Modell : glm-4.7-flash # Engine : llama.cpp # Run-ID : run-20260929-111253-2b4345 # GPU : 2x AMD Radeon RX 7900 XTX # CPU : AMD Ryzen Threadripper PRO 3955WX 16-Cores # RAM : 189 GB bench@llm-benchmark:~$ llama-server \ -m zai-org_GLM-4.7-Flash-Q4_K_M.gguf \ --alias glm-4.7-flash mode=gpu \ -c 24576 \ -np 10 '(2x' RX 7900 XTX + 196GB RAM 'Offload)'
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-4.7-flash
Kontextlaenge?Maximale Anzahl Tokens (Eingabe + erzeugte Ausgabe zusammen), die das Modell pro Anfrage verarbeiten kann.24576
Modellpfad?Pfad zur GGUF-Modelldatei, die geladen und ausgeliefert wird.zai-org_GLM-4.7-Flash-Q4_K_M.gguf
Kontext?Groesse des Kontextfensters in Token. 0 = der beim Training verwendete Kontext des Modells.24576
np10
execution_typelocal

All benchmarks of this model To leaderboard

Anzeige
Model comparison

glm-4.7-flash 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

18714410056,813,23.4543.7534.0534.353Prefill (tok/s)Generation (tok/s)NVIDIA GB10 (DGX Spark) - 48,9 tok/s Generation, 4.055 tok/s Prefill, TTFT 536 ms (1 Lauf)NVIDIA GB10 (DGX Spar...AMD Radeon RX 7900 XTX - 151,7 tok/s Generation, 3.752 tok/s Prefill, TTFT 3.439 ms (3 Laufe) | DIESER LAUF★ AMD Radeon RX 7900 XTX
★ AMD Radeon RX 7900 XTX 151,7 tok/s this runNVIDIA GB10 (DGX Spark) 48,9 tok/s

CPUby processor

18714410056,813,23.4543.7534.0534.353Prefill (tok/s)Generation (tok/s)NVIDIA Grace - 48,9 tok/s Generation, 4.055 tok/s Prefill, TTFT 536 ms (1 Lauf)NVIDIA GraceAMD Ryzen Threadripper PRO 3955WX 16-Cores - 151,7 tok/s Generation, 3.752 tok/s Prefill, TTFT 3.439 ms (3 Laufe) | DIESER LAUF★ AMD Ryzen Threadrippe...
★ AMD Ryzen Threadripper PRO 3955WX 16-Cores 151,7 tok/s this runNVIDIA Grace 48,9 tok/s

MBby mainboard

18714410056,813,23.4543.7534.0534.353Prefill (tok/s)Generation (tok/s)ASUSTeK COMPUTER INC. GX10 - 48,9 tok/s Generation, 4.055 tok/s Prefill, TTFT 536 ms (1 Lauf)ASUSTeK COMPUTER INC....ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI - 151,7 tok/s Generation, 3.752 tok/s Prefill, TTFT 3.439 ms (3 Laufe) | DIESER LAUF★ ASUSTeK COMPUTER INC....
★ ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI 151,7 tok/s this runASUSTeK COMPUTER INC. GX10 48,9 tok/s

ENGby engine

18714410056,813,23.4543.7534.0534.353Prefill (tok/s)Generation (tok/s)vLLM - 48,9 tok/s Generation, 4.055 tok/s Prefill, TTFT 536 ms (1 Lauf)vLLMllama.cpp - 151,7 tok/s Generation, 3.752 tok/s Prefill, TTFT 3.439 ms (3 Laufe) | DIESER LAUF★ llama.cpp
★ llama.cpp 151,7 tok/s this runvLLM 48,9 tok/s

DRVby driver

18714410056,813,23.4543.7534.0534.353Prefill (tok/s)Generation (tok/s)unbekannt - 151,7 tok/s Generation, 3.752 tok/s Prefill, TTFT 3.439 ms (3 Laufe)unbekanntNVIDIA 590.48.01 / CUDA 13.1 - 48,9 tok/s Generation, 4.055 tok/s Prefill, TTFT 536 ms (1 Lauf)NVIDIA 590.48.01 / CU...
unbekannt 151,7 tok/sNVIDIA 590.48.01 / CUDA 13.1 48,9 tok/s
💰 Economics

Economics of this run

Operating cost, TCO and comparison with the next-best runs of the same model at identical concurrency (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 10 W
⚡ TDP 720 W
☁️ External LLM (API)
Electricity0.30 EUR/kWh
Avg power (incl. idle)720 W estimated (TDP)GPU 710 + Board 10 W full load
Avg cost / hourEUR 0.22
Electricity / 1M tokensEUR 0.40
Token / kWh758.50K
Acquisition (system)EUR 3,790 partial priceGPU EUR 2,098 · RAM EUR 1,512 · PSU EUR 180
Electricity (2 years)–
TCO (2 years)EUR 7,574
Output tokens (2 years)9.57B
☁️ 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 (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

Comparison vs. API – economics per benchmark

glm-4.7-flash2x AMD Radeon RX 7900 XTX
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)–
2× AMD Radeon RX 7900 XTX · this run 152 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.