Unverified50% confidenceBenchmarkExact time
The 7900XTX on Windows achieves only approximately 400–479 t/s for the prompt processing (preview) phase with Qwen3 IQ3_XSS quantization.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/5/2026
First Seen
Valid until: 1/3/2027
Sources
Related Entities
Related Claims
UnverifiedQwen3.8 27B surpasses Opus 4.6 Max in visual performance on computer use and browser operation tasks.72% similarUnverifiedThe IQ3_S model is about 7 GB larger than IQ3_XXS and has a slightly slower generation speed.70% similarUnverifiedMuse Glimmer 30B is reported to achieve 74.9 tokens per second on an RTX 5090, and reviewers observed approximately 60–65 tokens/sec running the full-precision version on an RTX 3090.70% similarUnverifiedIn Strata's speed table, under a 128k context, Q2_0 (2-bit) achieves 65.1 tokens/s and IQ2_XS achieves 52 tokens/s; under a 4k short context, IQ3_XXS achieves 65.6 tokens/s.68% similarUnverifiedIn Path A, an RTX 3060 runs the front layers and an AMD AI Max+ 395 runs the back layers, improving Prefill speed from 136.69 token/s to 319.1 token/s under IQ3 quantization with 64K long input.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/978758API
curl https://kongchang.com/api/v1/knowledge/claims/978758MCP
get_claim(id=978758)