Unverified50% confidenceBenchmarkExact time
Using an AMD Radeon RX 7900XTX on Windows 11 to run Qwen3 via Strata, the generation speed (output tokens) is stable at 60–80 t/s, averaging approximately 68 tokens/s.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/5/2026
First Seen
Valid until: 1/3/2027
Sources
Related Entities
Related Claims
UnverifiedIn benchmark testing on an AMD RX 7900 GPU, Ornith 35B achieved an overall accuracy of 85% (18 out of 21 passed), a generation speed of 74 tokens/s, a prompt processing speed of 850 tokens/s, and a VRAM usage of 20 GB.69% similarVerifiedIn an RTX 5070 (12GB VRAM) configuration, the local Qwen3 9B model's output speed reached approximately 70–76 tokens/second.68% similarUnverifiedRunning 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.68% similarUnverifiedThe core of the build is four AMD Radeon Pro V620 graphics cards, totaling approximately $1,400, providing 128GB of combined VRAM.65% similarUnverifiedThe RX 7900 XTX can achieve speeds of 60–100 tokens/second when running Flash-series models of approximately the 7B scale.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/978757API
curl https://kongchang.com/api/v1/knowledge/claims/978757MCP
get_claim(id=978757)