N
Manufacturer
NVIDIA
Nemotron-Modellfamilie von NVIDIA.
Best token generation
3.484,3 tok/s
NVIDIA-Nemotron-3.5-Lightning-30B-A3B
Best prefill
44.171,1 tok/s
NVIDIA-Nemotron-3-Nano-4B
∅ Token generation
275,1 tok/s
Average of 669 runs
∅ Prefill
3.818,4 tok/s
Average of 667 runs
Best TTFT
31 ms
NVIDIA-Nemotron-3.5-Lightning-30B-A3B
Best harness rate
80%
Nemotron-Cascade-2-30B-A3B
🏆
NVIDIA-Nemotron-3.5-Lightning-30B-A3B · fastest model at 3.484,3 tok/s token generation
Best prefill of this manufacturer: 44.171,1 tok/s (NVIDIA-Nemotron-3-Nano-4B)
Best prefill of this manufacturer: 44.171,1 tok/s (NVIDIA-Nemotron-3-Nano-4B)
Top models by token generation
Best measured generation throughput per model (tok/s), published performance benchmarks.
Models
All benchmarks →14 assigned
Llama-3_1-Nemotron-Ultra-253B-v1253B53 runs
4,3tok/s Ø
Min 0,1Max 62,1
Llama-3_3-Nemotron-Super-49B-v1_549B49 runs
75,4tok/s Ø
Min 1,1Max 364,1
Llama-3.1-Nemotron-Nano-4B-v1.14.5B8 runs
229,5tok/s Ø
Min 49,2Max 419,4
Nemotron-3-Nano-Omni-30B-A3B-Reasoning30B64 runs
432,5tok/s Ø
Min 31,4Max 1.791,5
Nemotron-3-Super-120B-A12B-Q8120B0 runs
No performance data yet
Nemotron-Cascade-2-30B-A3B30B81 runs
385,5tok/s Ø
Min 0,3Max 1.784,7
Nemotron-H-47B-Reasoning-128K47B63 runs
45,1tok/s Ø
Min 1,1Max 203,5
NVIDIA-Nemotron-3-Nano-30B-A3B30B94 runs
359,3tok/s Ø
Min 0,3Max 1.775,6
NVIDIA-Nemotron-3-Nano-4B4B72 runs
548,7tok/s Ø
Min 0,3Max 2.182,7
NVIDIA-Nemotron-3-Super-120B-A12B120B59 runs
81,4tok/s Ø
Min 1,9Max 600,9
NVIDIA-Nemotron-3.5-Lightning-30B-A3B31.6B69 runs
446,9tok/s Ø
Min 50,7Max 3.484,3
NVIDIA-Nemotron-3.5-Super-VL-120B-A12B120B6 runs
445,0tok/s Ø
Min 20,4Max 1.562,3
NVIDIA-Nemotron-Labs-3-Puzzle-75B-A9B75B0 runs
No performance data yet
OpenReasoning-Nemotron-32B32B53 runs
107,9tok/s Ø
Min 1,1Max 481,0

