Created bymario-alka.dePowered bygodcore.de noob2claw.de tricoma.de

Sign in Sign up

Beta

Open data · reproducible tests

Which model is fast & smart?

We benchmark AI language models on real hardware: speed in tokens per second and response time – plus quality on real agent tasks. Transparent, reproducible, directly comparable.

Start typing – or jump straight in:Fastest (tok/s)Best harness All models Makers Highscore

4756 benchmarks110 models2 test types

Live benchmark

Who generates text the fastest? Real measurements, real hardware.

1

gemma-4-E2B-itGeForce RTX 5090

2.491,2tok/s

2

Nemotron-3.5-Lightning-30B-A3BGeForce RTX 3090 Ti

2.263,7tok/s

3

Nemotron-3-Nano-4BRTX PRO 6000 Blackwe

2.182,7tok/s

4

gpt-oss-20bRTX PRO 6000 Blackwe

1.995,4tok/s

5

Ornith-1.0-35BRTX PRO 6000 Blackwe

1.799,4tok/s

Peak2.491tok/s

View ranking →

01

Real performance

TTFT, prefill and generation tokens/s instead of theoretical peak numbers.

02

Harness quality

Points and success rates from complete agent and chat runs.

03

Full transparency

Model, quantization, runtime and hardware stay visible on every run.

Community favorites

Top models by benchmarks

Speed (tokens/s) and quality (harness) of the most-tested models – directly comparable.

Qwen3.6-35B-A3B

⚡ Speed1.489,1 tok/s

🏆 Quality–

166 Benchmarks166 Perf.0 Harness

gpt-oss-20b

⚡ Speed1.995,4 tok/s

🏆 Quality–

155 Benchmarks155 Perf.0 Harness

Qwen3-30B-A3B-Instruct-2507

⚡ Speed1.671,0 tok/s

🏆 Quality–

131 Benchmarks131 Perf.0 Harness

Qwen3-Coder-30B-A3B-Instruct

⚡ Speed1.716,6 tok/s

🏆 Quality–

129 Benchmarks129 Perf.0 Harness

Laguna-XS-2.1

⚡ Speed1.765,0 tok/s

🏆 Quality–

127 Benchmarks127 Perf.0 Harness

Ministral-3-14B-Reasoning-2512

⚡ Speed1.060,0 tok/s

🏆 Quality–

123 Benchmarks123 Perf.0 Harness

Current measurements

Leaderboard Snapshot

Alle Ergebnisse →

Metric:

Size

GPUs

	#	Model / Maker	Metrics	Parallel	GPU / CPU / RAM	Runtime
	1	gemma-4-E2B-it5BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)	2.491,20 tok/s TG Prefill 15.814 · TTFT 4.382 ms	10×	NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM	llama.cppcodex_cliQ4_K_M	Details →
	2	gemma-4-E2B-it5BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)	2.414,37 tok/s TG Prefill 20.277 · TTFT 4.107 ms	10×	NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM	llama.cppgodclawQ4_K_M	Details →
	3	Nemotron-3.5-Lightning-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)	2.263,71 tok/s TG Prefill 9.016 · TTFT 21.818 ms	10×	NVIDIA GeForce RTX 3090 TiAMD Ryzen 5 5600X 6-Core Processor · 30 GB RAM	vLLMvllmNVFP4	Details →
	4	Nemotron-3-Nano-4B4BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)	2.182,67 tok/s TG Prefill 10.599 · TTFT 5.598 ms	10×	NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM	llama.cppgodclawQ4_K_M	Details →
	5	gemma-4-E2B-it5BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)	2.143,55 tok/s TG Prefill 13.632 · TTFT 4.819 ms	10×	3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM	llama.cppgodclawQ4_K_M	Details →

Hardware ranking

Benchmarks by graphics card

Generation throughput (tokens/s) per GPU – minimum, average and maximum across all performance runs.

NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition542 Läufe

Min 7,0Max 2.143,6

NVIDIA RTX PRO 6000 Blackwell Workstation Edition244 Läufe

Min 0,0Max 2.414,4

NVIDIA GeForce RTX 30906 Läufe

Min 50,5Max 1.132,7

NVIDIA GeForce RTX 5090218 Läufe

Min 0,1Max 2.491,2

NVIDIA GeForce RTX 3090 Ti273 Läufe

Min 0,0Max 2.263,7

NVIDIA RTX A60001028 Läufe

Min 5,0Max 1.568,0

NVIDIA GeForce RTX 409017 Läufe

Min 42,3Max 503,3

NVIDIA GeForce RTX 5070 Ti222 Läufe

Min 0,7Max 1.744,0

AMD Radeon RX 7900 XTX361 Läufe

Min 0,1Max 717,6

NVIDIA GB1097 Läufe

Min 11,4Max 903,3

Intel Arc Pro B7032 Läufe

Min 0,0Max 826,2

AMD Oberon (PlayStation 5)9 Läufe

Min 10,6Max 302,6

NVIDIA Tesla V100 PCIe 32GB39 Läufe

Min 2,3Max 361,8

AMD Radeon PRO W7800 48GB164 Läufe

Min 3,4Max 702,9

AMD Radeon PRO W7900 Dual Slot241 Läufe

Min 8,0Max 344,1

AMD Radeon AI PRO R9700978 Läufe

Min 0,0Max 667,0

NVIDIA GeForce RTX 206077 Läufe

Min 1,1Max 259,9

AMD Radeon 8060S Graphics50 Läufe

Min 7,0Max 326,9

AMD Liverpool (PlayStation 4)1 Läufe

Min 43,2Max 43,2

NVIDIA Tesla P100 PCIe 16GB28 Läufe

Min 13,3Max 111,1

Hardware ranking

Benchmarks by CPU

Generation throughput (tokens/s) per CPU – minimum, average and maximum across all performance runs.

AMD Ryzen Threadripper PRO 9965WX 24-Cores510 Läufe

Min 9,4Max 2.143,6

AMD Ryzen 9 9950X 16-Core Processor247 Läufe

Min 0,0Max 2.414,4

AMD Ryzen 7 5800X3D 8-Core Processor218 Läufe

Min 0,1Max 2.491,2

AMD Ryzen Threadripper PRO 3945WX 12-Cores6 Läufe

Min 115,5Max 1.171,8

AMD Ryzen 5 5600X 6-Core Processor57 Läufe

Min 21,3Max 2.263,7

AMD Ryzen 9 8945HX with Radeon Graphics222 Läufe

Min 0,0Max 1.492,8

AMD Ryzen 9 7945HX with Radeon Graphics96 Läufe

Min 0,0Max 1.564,6

AMD Ryzen Threadripper PRO 3955WX 16-Cores189 Läufe

Min 9,9Max 717,6

AMD Ryzen Threadripper PRO 7955WX 16-Cores1856 Läufe

Min 0,0Max 1.568,0

AMD Ryzen 3 3100 4-Core Processor137 Läufe

Min 21,9Max 561,4

NVIDIA Grace96 Läufe

Min 11,4Max 903,3

AMD Zen2 8-Core (PlayStation 5)9 Läufe

Min 10,6Max 302,6

AMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics35 Läufe

Min 35,1Max 361,8

AMD Ryzen Threadripper PRO 5975WX 32-Cores621 Läufe

Min 0,7Max 1.744,0

Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz214 Läufe

Min 0,1Max 609,5

AMD EPYC 7203P 8-Core Processor30 Läufe

Min 9,0Max 388,1

Intel(R) Core(TM) i5-7400 CPU @ 3.00GHz39 Läufe

Min 6,8Max 133,7

AMD RYZEN AI MAX+ 395 w/ Radeon 8060S50 Läufe

Min 7,0Max 326,9

AMD Jaguar 8-Core (PlayStation 4)4 Läufe

Min 1,3Max 43,2

4 x Cortex-A78C + 4 x Cortex-A5531 Läufe

Min 0,0Max 19,6

Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz38 Läufe

Min 0,0Max 14,5