Manufacturer

HuggingFaceTB

Manufacturer profile and assigned models.

🤗 Hugging Face Filter in leaderboard

1Models

5Benchmarks

5Performance

0Harness

Best token generation

531,7 tok/s

SmolLM2-1.7B-Instruct

Best prefill

44.141,4 tok/s

SmolLM2-1.7B-Instruct

∅ Token generation

189,7 tok/s

Average of 5 runs

∅ Prefill

18.212,1 tok/s

Average of 5 runs

Best TTFT

223 ms

SmolLM2-1.7B-Instruct

Best harness rate

no harness run yet

🏆

SmolLM2-1.7B-Instruct · fastest model at 531,7 tok/s token generation
Best prefill of this manufacturer: 44.141,4 tok/s (SmolLM2-1.7B-Instruct)

Top models by token generation

Best measured generation throughput per model (tok/s), published performance benchmarks.

SmolLM2-1.7B-Instruct

531,7 tok/s

Models

1 assigned

All benchmarks →

SmolLM2-1.7B-Instruct1.7B5 runs

189,7tok/s Ø

Min 2,9Max 531,7