Unverified50% confidenceBenchmarkExact time
The closed-source Hologen Flash Server (Linux) can achieve a prefill speed of 1,200 to 1,400 tokens, outperforming GFX1151 Engine.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/5/2026
First Seen
Valid until: 1/3/2027
Sources
Related Entities
Related Claims
UnverifiedThe RX 7900 XTX can achieve speeds of 60–100 tokens/second when running Flash-series models of approximately the 7B scale.73% similarUnverifiedZhipu has released GLM-4.5 FlashX, reaching a maximum speed of 200 tokens/second, with the API now live.69% similarUnverifiedThe DeepSeek Flash model can output more than 100 tokens per second.67% similarUnverifiedThe Qwen3.8 Flash Next (Q3 quantized version) weights are approximately 84 GB and run on an AMD 7900XTX 24 GB GPU with an average decoding output speed of approximately 90 tokens/s.66% similarUnverifiedDeepSeek V4 Flash is a cloud-based model focused on high throughput, with an inference speed of approximately 140 tokens per second.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/978821API
curl https://kongchang.com/api/v1/knowledge/claims/978821MCP
get_claim(id=978821)