Unverified50% confidenceBenchmarkExact time
On a single H100 and at similar measured accuracy, QwenDLM-4B + ORL reaches 1,298 tokens/s, DFlash 746 tokens/s, and EAGLE3 405 tokens/s (end-to-end system comparison: ORL runs on dlmrt, speculative decoding runs on vLLM).
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/17/2026
First Seen
Valid until: 10/31/2026
Sources
Related Entities
Related Claims
UnverifiedIn the scenario where 16 requests each carry a 3,072-token long prompt, Gemma 4 E2B maintains 1049 tokens/second, while Granite 3.3 2B drops to 732 (0.70x), SmolLM3-3B drops to 725 (0.69x), Phi-4-mini drops to 404 (0.39x), and Qwen3-4B reaches only 373 (0.36x).73% similarUnverifiedThe Chinchilla model, with 70B parameters and 1.4T tokens, significantly outperforms the Gopher model, which has 280B parameters and 300B tokens, under the same compute budget.72% similarUnverifiedIn the 16-concurrency, 256-token-output test, Gemma 4 E2B achieves an output speed of 1887 tokens/second, and the models faster than it include Qwen2.5-0.5B (4176, 2.21x), Qwen3-0.6B (3210, 1.70x), Qwen2.5-1.5B (2780, 1.47x), and Qwen3-1.7B (2049, 1.09x).71% similarUnverifiedIn an ultra-long context test, Ornith 1.5 ran at around 75 tokens/second early on and dropped to approximately 45 tokens/second after exceeding 1.6 million tokens, while Qwen 3.8 dropped to approximately 5 tokens/second under the same load.70% similarUnverifiedUnder conditions of 2944 input tokens and 1024 output tokens, normal mode reaches 29.9 tokens per second, which improves to 48.4 tokens/s after enabling MTP2.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1049951API
curl https://kongchang.com/api/v1/knowledge/claims/1049951MCP
get_claim(id=1049951)