Unverified50% confidenceBenchmarkExact time
A reproducer measured HyperQwen's real chat-scenario throughput on an RTX 3090 at about 118 tok/s (greedy decoding averaged 118.1 tok/s across four prompts, range 111-131; 123.3 tok/s under temperature 0.7 sampling), far below 381 tok/s.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/16/2026
First Seen
Valid until: 10/30/2026
Sources
Related Entities
Related Claims
UnverifiedThe comparison baseline Q4_K_M GGUF version runs at about 42 tok/s on llama.cpp on the same card (RTX 3090); HyperQwen is about three times faster in real chat and about six times faster in citation scenarios.74% similarUnverifiedOn an RTX 5070 with a 6-core Ryzen and 64 GB of memory, Strata achieves approximately 90 tokens/second for short conversations, approximately 67 tokens/second at a 128,000-token context, and approximately 1,300 tokens/second for reading prompts.68% similarUnverifiedRTX 4090相比RTX 3060在推理场景下的实际吞吐量提升约3-4倍65% similarUnverifiedWhen running Whisper ASR, a TTS voice model, and nomic-embed-text simultaneously on an RTX 3090 with 24 GB of VRAM, the three resident models occupied 17.8 GB (72%) of VRAM, peaked at 23.4 GB over the course of a week, and never spilled over into system memory.65% similarVerifiedIn an RTX 5070 (12GB VRAM) configuration, the local Qwen3 9B model's output speed reached approximately 70–76 tokens/second.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1043370API
curl https://kongchang.com/api/v1/knowledge/claims/1043370MCP
get_claim(id=1043370)