Unverified50% confidenceBenchmarkExact time
The MESA 26.1 driver doubled the B70's Vulkan path performance on MoE-type models like Qwen3 30B-A3B from 38 to 76 tokens/s, approaching the R9700's approximately 77 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 token generation tests for the Gemma 4 12B model, Spark reached 26.4 tokens/s, Halo 24.6 tokens/s, and M4 Pro was the fastest at 33.8 tokens/s.68% similarUnverifiedOfficial benchmark results show that the Qwen3.6 35B MoE model can reach 1.38k token/s at 8 concurrency.66% 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.65% similarVerifiedQwen3.6 27B scored 77.2 on SWE-bench Verified.59% similarUnverifiedThe standard Kimi-K3-REAP-512GB version completely failed on SWE-Lancer tasks 14294, 15815_1, and 15925.57% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/977979API
curl https://kongchang.com/api/v1/knowledge/claims/977979MCP
get_claim(id=977979)