Unverified50% confidenceFactExact time
Qwen3.8-Flash-Next on MLX is up to 1.4 times faster on M5 Macs and up to 1.2 times faster on M1 through M4.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/19/2026
First Seen
Valid until: 1/17/2027
Sources
Related Entities
Related Claims
UnverifiedOn the RTX 5090, using D-Flash speculative decoding can achieve a speedup of more than 3x, while the improvement on Mac M4/M5 is between 1.5x and 1.8x.78% similarUnverifiedQwen3.5 with approximately 800 million parameters achieved the fastest generation speed, approaching 15 tokens per second, with the second-place LFM2.5 exceeding 10 tokens per second.71% similarUnverifiedOn the M5 Max chip, Lily's prefill speed is 1.23× faster than MLX-LM and its decode speed is 1.35× faster (official data).71% similarUnverifiedThe Q4_K_M/GGUF version of Qwen 27B decodes at approximately 10.7 tok/s on the same machine, roughly 1/3.8 of the MLX version.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1070385API
curl https://kongchang.com/api/v1/knowledge/claims/1070385MCP
get_claim(id=1070385)