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

Ling-3.0-flash

Performance benchmark · measured on 25.09.2026 13:12

Benchmark-IDrun-20260925-112847-c08ea4
Timebench 3 - Kombi (Prefill + Generation)MoE127.5BRuntime: llama.cppQuantisierung: Q4_K_M
Generation12,73tok/s
Prefill128,56tok/s
Time to First Token58.150,00ms
Total duration283,86s
Concurrency1parallel
Ranking in the field
102of 115 systems

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

This run is better than 11 % of all comparable systems.
Generation 12,7 tok/s
-81 % vs Ø 68,4
Prefill 128,6 tok/s
-96 % vs Ø 3.306,7
Time to First Token 58.150 ms
+1.129 % vs Ø 4.731
Distribution in the field1 – 244 tok/s
Ø 68 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)

Hardware

GPU: 2x AMD Radeon RX 7900 XTX · 24 GB VRAM
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-20260925-112847-c08ea4
# LLM-Benchmark Konfiguration # Modell : Ling-3.0-flash # Engine : llama.cpp # Run-ID : run-20260925-112847-c08ea4 # GPU : 2x AMD 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
execution_typelocal

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

47836926115243,101.3262.6523.978Prefill (tok/s)Generation (tok/s)NVIDIA RTX A6000 - 388,1 tok/s Generation, 3.235 tok/s Prefill, TTFT 7.234 ms (15 Laufe)NVIDIA RTX A6000NVIDIA 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...AMD Radeon RX 7900 XTX - 133,0 tok/s Generation, 184 tok/s Prefill, TTFT 122.114 ms (7 Laufe) | DIESER LAUF★ AMD Radeon RX 7900 XTX
NVIDIA RTX A6000 388,1 tok/sNVIDIA GB10 (DGX Spark) 253,7 tok/sAMD Radeon PRO W7900 Dual Slot 165,7 tok/sAMD Radeon AI PRO R9700 160,2 tok/s★ AMD Radeon RX 7900 XTX 133,0 tok/s this run

CPUby processor

5013762511250,001.3302.6613.991Prefill (tok/s)Generation (tok/s)AMD EPYC 7203P 8-Core Processor - 388,1 tok/s Generation, 3.235 tok/s Prefill, TTFT 7.234 ms (15 Laufe)AMD EPYC 7203P 8-Core...10 x ARM implementer 0x41, part 0xd87 + 10 x ARM implementer 0x41, part 0xd85 - 253,7 tok/s Generation, 1.278 tok/s Prefill, TTFT 22.647 ms (15 Laufe)10 x ARM implementer ...AMD 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...Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz - 14,9 tok/s Generation, 109 tok/s Prefill, TTFT 109.414 ms (3 Laufe)Intel(R) Xeon(R) CPU ...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...
AMD EPYC 7203P 8-Core Processor 388,1 tok/s10 x ARM implementer 0x41, part 0xd87 + 10 x ARM implementer 0x41, part 0xd85 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 runIntel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz 14,9 tok/s

MBby mainboard

5013762511250,001.8743.7485.622Prefill (tok/s)Generation (tok/s)ASRockRack ROMED8-2T/BCM - 388,1 tok/s Generation, 4.550 tok/s Prefill, TTFT 4.923 ms (9 Laufe)ASRockRack ROMED8-2T/...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....Dell Inc. PowerEdge R820 - 14,9 tok/s Generation, 109 tok/s Prefill, TTFT 109.414 ms (3 Laufe)Dell Inc. PowerEdge R...ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI - 194,7 tok/s Generation, 1.079 tok/s Prefill, TTFT 21.150 ms (37 Laufe) | DIESER LAUF★ ASUSTeK COMPUTER INC....
ASRockRack ROMED8-2T/BCM 388,1 tok/sASUSTeK COMPUTER INC. GX10 253,7 tok/s★ ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI 194,7 tok/s this runASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE 160,2 tok/sDell Inc. PowerEdge R820 14,9 tok/s

ENGby engine

45438732125418804.0978.19312.290Prefill (tok/s)Generation (tok/s)vLLM - 388,1 tok/s Generation, 10.088 tok/s Prefill, TTFT 1.544 ms (3 Laufe)vLLMllama.cpp - 253,7 tok/s Generation, 1.220 tok/s Prefill, TTFT 19.532 ms (84 Laufe) | DIESER LAUF★ llama.cpp
vLLM 388,1 tok/s★ llama.cpp 253,7 tok/s this run

DRVby driver

4274073883693491.4341.4951.5561.617Prefill (tok/s)Generation (tok/s)unbekannt - 388,1 tok/s Generation, 1.526 tok/s Prefill, TTFT 18.911 ms (87 Laufe)unbekannt
unbekannt 388,1 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 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 4.71
Token / kWh63.65K
Acquisition (system)EUR 2,782 partial priceGPU EUR 2,098 · RAM EUR 504 · PSU EUR 180
Electricity (2 years)–
TCO (2 years)EUR 6,566
Output tokens (2 years)802.91M
☁️ 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

Ling-3.0-flash2x AMD Radeon RX 7900 XTXLing-3.0-flash2x NVIDIA RTX A6000Ling-3.0-flash2x NVIDIA RTX A6000Ling-3.0-flash2x NVIDIA RTX A6000
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.