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

Ling-3.0-flash

Performance benchmark · measured on 25.09.2026 13:45

Benchmark-IDrun-20260925-120144-a6ab54
Timebench 3 - Kombi (Prefill + Generation)MoE127.5BRuntime: llama.cppQuantisierung: Q4_K_M
Generation132,97tok/s
Prefill378,92tok/s
Time to First Token285.990,00ms
Total duration1.200,00s
Concurrency10parallel
Ranking in the field
1of 1 systems

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

This run is better than 100 % of all comparable systems.
Generation 133,0 tok/s
+0 % vs Ø 133,0
Prefill 378,9 tok/s
+0 % vs Ø 378,9
Time to First Token 285.990 ms
+0 % vs Ø 285.990

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: 2x Radeon RX 7900 XTX
CPU: AMD Ryzen Threadripper PRO 3955WX 16-Cores
RAM: 63 GB
Mainboard: ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI

Setup

Runtime: llama.cpp
Quantization: Q4_K_M
Model: Ling-3.0-flash

Configuration

benchmark-konfiguration — run-20260925-120144-a6ab54
# LLM-Benchmark Konfiguration # Modell : Ling-3.0-flash # Engine : llama.cpp # Run-ID : run-20260925-120144-a6ab54 # GPU : 2x Radeon RX 7900 XTX # CPU : AMD Ryzen Threadripper PRO 3955WX 16-Cores # RAM : 63 GB bench@llm-benchmark:~$ llama-server Ling-3.0-flash-Q4_K_M \ -ngl 99 \ --n-cpu-moe 32 '(2x' RX 7900 XTX, 'Expert-CPU-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
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.99
n-cpu-moe32

All benchmarks of this model To leaderboard

Anzeige
Model comparison

Ling-3.0-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

31124217310435,005671.1341.702Prefill (tok/s)Generation (tok/s)NVIDIA GB10 (DGX Spark) - 253,7 tok/s Generation, 1.278 tok/s Prefill, TTFT 22.647 ms (15 Laufe)NVIDIA GB10 (DGX Spar...AMD Radeon PRO W7900 Dual Slot - 165,7 tok/s Generation, 1.163 tok/s Prefill, TTFT 7.103 ms (27 Laufe)AMD Radeon PRO W7900 ...AMD Radeon AI PRO R9700 - 160,2 tok/s Generation, 1.407 tok/s Prefill, TTFT 6.543 ms (23 Laufe)AMD Radeon AI PRO R97...NVIDIA RTX A6000 - 92,6 tok/s Generation, 933 tok/s Prefill, TTFT 14.121 ms (3 Laufe)NVIDIA RTX A6000Radeon RX 7900 XTX - 133,0 tok/s Generation, 240 tok/s Prefill, TTFT 131.640 ms (4 Laufe) | DIESER LAUF★ Radeon RX 7900 XTX
NVIDIA GB10 (DGX Spark) 253,7 tok/sAMD Radeon PRO W7900 Dual Slot 165,7 tok/sAMD Radeon AI PRO R9700 160,2 tok/s★ Radeon RX 7900 XTX 133,0 tok/s this runNVIDIA RTX A6000 92,6 tok/s

CPUby processor

31124217310435,005671.1341.702Prefill (tok/s)Generation (tok/s)NVIDIA Grace - 253,7 tok/s Generation, 1.278 tok/s Prefill, TTFT 22.647 ms (15 Laufe)NVIDIA GraceAMD Ryzen Threadripper PRO 5975WX 32-Cores - 165,7 tok/s Generation, 1.163 tok/s Prefill, TTFT 7.103 ms (27 Laufe)AMD Ryzen Threadrippe...AMD Ryzen Threadripper PRO 7955WX 16-Cores - 160,2 tok/s Generation, 1.407 tok/s Prefill, TTFT 6.543 ms (23 Laufe)AMD Ryzen Threadrippe...AMD EPYC 7203P 8-Core Processor - 92,6 tok/s Generation, 933 tok/s Prefill, TTFT 14.121 ms (3 Laufe)AMD EPYC 7203P 8-Core...AMD Ryzen Threadripper PRO 3955WX 16-Cores - 133,0 tok/s Generation, 240 tok/s Prefill, TTFT 131.640 ms (4 Laufe) | DIESER LAUF★ AMD Ryzen Threadrippe...
NVIDIA Grace 253,7 tok/sAMD Ryzen Threadripper PRO 5975WX 32-Cores 165,7 tok/sAMD Ryzen Threadripper PRO 7955WX 16-Cores 160,2 tok/s★ AMD Ryzen Threadripper PRO 3955WX 16-Cores 133,0 tok/s this runAMD EPYC 7203P 8-Core Processor 92,6 tok/s

MBby mainboard

2982522071621168821.1081.3331.559Prefill (tok/s)Generation (tok/s)ASUSTeK COMPUTER INC. GX10 - 253,7 tok/s Generation, 1.278 tok/s Prefill, TTFT 22.647 ms (15 Laufe)ASUSTeK COMPUTER INC....ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE - 160,2 tok/s Generation, 1.407 tok/s Prefill, TTFT 6.543 ms (23 Laufe)ASUSTeK COMPUTER INC....ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI - 165,7 tok/s Generation, 1.034 tok/s Prefill, TTFT 22.374 ms (34 Laufe) | DIESER LAUF★ ASUSTeK COMPUTER INC....
ASUSTeK COMPUTER INC. GX10 253,7 tok/s★ ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI 165,7 tok/s this runASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE 160,2 tok/s

ENGby engine

2792662542412281.1321.1801.2281.276Prefill (tok/s)Generation (tok/s)llama.cpp - 253,7 tok/s Generation, 1.204 tok/s Prefill, TTFT 17.374 ms (72 Laufe) | DIESER LAUF★ llama.cpp
★ llama.cpp 253,7 tok/s this run

DRVby driver

2972532101661231.0911.1841.2781.371Prefill (tok/s)Generation (tok/s)NVIDIA 590.48.01 / CUDA 13.1 - 253,7 tok/s Generation, 1.278 tok/s Prefill, TTFT 22.647 ms (15 Laufe)NVIDIA 590.48.01 / CU...unbekannt - 165,7 tok/s Generation, 1.185 tok/s Prefill, TTFT 15.986 ms (57 Laufe)unbekannt
NVIDIA 590.48.01 / CUDA 13.1 253,7 tok/sunbekannt 165,7 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 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 0.0063
Token / kWh47.87M
Acquisition (system)EUR 624 missingRAM EUR 504 · PSU EUR 120
Electricity (2 years)–
TCO (2 years)EUR 677
Output tokens (2 years)8.39B
☁️ 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

Comparison vs. API – economics per benchmark

Ling-3.0-flash2x Radeon RX 7900 XTXLing-3.0-flashNVIDIA GB10 (DGX Spark)Ling-3.0-flashNVIDIA GB10 (DGX Spark)Ling-3.0-flashNVIDIA GB10 (DGX Spark)
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.