Prince Canuma
@Prince_Canuma
@neywalabs founder โข creator of (@Nativ_AI, MLX-VLM and MLX-Audio)
Ex-@arcee_ai โข @neptune_ai โข
๊ฐ์
July 2012
1.3K ํ๋ก์ ์ค 24.1K ํฌ
LFM2.5 DSpark by @liquidai is coming to mlx-vlm in v0.6.16 โก๏ธ
Exact speculative decoding on M5 Max, delivering up to 3.7ร faster generation with zero output drift.
On-device speed, zero output drift.
Benchmarks below ๐งต
๋ ๋ณด๊ธฐ
