Unverified50% confidenceBenchmarkExact time
The 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.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/16/2026
First Seen
Valid until: 10/30/2026
Sources
Related Entities
Related Claims
UnverifiedA 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.74% similarUnverifiedQwen3.5 with approximately 800 million parameters achieved the fastest generation speed, approaching 15 tokens per second, with the second-place LFM2.5 exceeding 10 tokens per second.65% similarUnverifiedThe Q4_K_M/GGUF version of Qwen 27B decodes at approximately 10.7 tok/s on the same machine, roughly 1/3.8 of the MLX version.64% similarUnverifiedA Bilibili uploader used llama.cpp to load the 1-bit quantized version of GLM 5.3 Flash on 4 RTX 3090s, achieving a generation speed of 33.5 tok/s.63% similarUnverifiedWhen running Qwen3 27B (MXFP4) at 16 concurrent sessions, aggregate prefill reaches 6,300–6,800 tok/s, and aggregate decode throughput peaks at approximately 900 tok/s.63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1043375API
curl https://kongchang.com/api/v1/knowledge/claims/1043375MCP
get_claim(id=1043375)