Hugging Face's logo

Collections

Discover the best community collections!

Collections trending this week
Qwen3.6-27B oQe (MLX)
oMLX oQe mixed-precision MLX quantizations of Qwen/Qwen3.6-27B, bf16 and fp16 builds
K2-Horizon MoVA: MLA + SeedLM
K2-Horizon-MoVA-36B-A4B with multi-head latent attention (TransMLA, 2.3x smaller KV cache) and SeedLM seed weights, vs oQe.
K2-Horizon MoVA: MLA + SeedLM
K2-Horizon-MoVA-36B-A4B with multi-head latent attention (TransMLA, 2.3x smaller KV cache) and SeedLM seed weights, vs oQe.
Qwen3.6-27B oQe (MLX)
oMLX oQe mixed-precision MLX quantizations of Qwen/Qwen3.6-27B, bf16 and fp16 builds