Kimi-K3-mlx mlx-community/Kimi-K3-mlx-reap160-2bit Text Generation • 543B • Updated Aug 3 • 2.02k • 2
Nemotron-VoiceChat-11B-mlx On-Device SSM Duplex with MLX mlx-community/NemotronLabs-VoiceChat-11B-mlx-bf16 11B • Updated Aug 5 • 94 • 3 mlx-community/NemotronLabs-VoiceChat-11B-mlx-8bit 4B • Updated Aug 5 • 171 • 7 mlx-community/NemotronLabs-VoiceChat-11B-mlx-4bit 3B • Updated Aug 5 • 63 • 2
Kimi-K3-mlx mlx-community/Kimi-K3-mlx-reap160-2bit Text Generation • 543B • Updated Aug 3 • 2.02k • 2
Nemotron-VoiceChat-11B-mlx On-Device SSM Duplex with MLX mlx-community/NemotronLabs-VoiceChat-11B-mlx-bf16 11B • Updated Aug 5 • 94 • 3 mlx-community/NemotronLabs-VoiceChat-11B-mlx-8bit 4B • Updated Aug 5 • 171 • 7 mlx-community/NemotronLabs-VoiceChat-11B-mlx-4bit 3B • Updated Aug 5 • 63 • 2
Sleeping Agents Voice Memory Leaderboard 🎙 LLM correction over fixed ASR/ST n-best lists (WER/BLEU/ρ)