Unverified50% confidenceBenchmarkExact time
Running a Qwen3 27B-level model on an AMD RX 7900XTX 24GB GPU, the output speed can reach up to 52–53 TPS, with an average stable speed of around 47 TPS.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/6/2026
First Seen
Valid until: 12/5/2026
Sources
Related Entities
Related Claims
UnverifiedIn this configuration, Qwen3 27B achieves approximately 70 T/s natively in llama.cpp, with a measured peak of 76 T/s.73% similarUnverifiedIn an RTX 5070 (12GB VRAM) configuration, the local Qwen3 9B model's output speed reached approximately 70–76 tokens/second.71% similarUnverifiedAfter switching from Ollama to LM Studio and retuning parameters on an AMD 7900XT GPU, the token generation speed increased from 5 to 36 tokens per second.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/866084API
curl https://kongchang.com/api/v1/knowledge/claims/866084MCP
get_claim(id=866084)