Unverified50% confidenceBenchmarkExact time
In 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.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/5/2026
First Seen
Valid until: 1/3/2027
Sources
Related Entities
Related Claims
UnverifiedAt a 128K context, Q2_0 outputs 65.1 tok/s, IQ2_XS outputs 52.0 tok/s, and IQ3_XXS outputs 44.8 tok/s.80% 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.76% similarUnverifiedWith a 32K prompt input, the Q2 quantization read speed can increase from 572 tokens/s to 1,290 tokens/s, and Q3 can increase from 383 to 1,208 tokens/s.71% similarUnverifiedQwen 3.8 has a base speed of 22 tokens/s on the M5 Max, which can be boosted to 34 or even 56 tokens/s with MTP enabled.70% similarUnverifiedThe 7900XTX on Windows achieves only approximately 400–479 t/s for the prompt processing (preview) phase with Qwen3 IQ3_XSS quantization.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/978809API
curl https://kongchang.com/api/v1/knowledge/claims/978809MCP
get_claim(id=978809)