No official torrent yet — requesting it tells the flock what to host next. You cannot seed a catalog-only page.
Cataloged from AtomicChat/Qwen3.6-27B-MLX-4bit
All models by AtomicChat →
Qwen3.6 27B, self-quantized to MLX by Atomic Chat. Built straight from Qwen's original weights with a per-tensor importance matrix, so this is not a repack of somebody else's files. Runs fully offline.
[!NOTE] These MLXs are self-quantized from the original weights, not a repack. The importance matrix keeps low-bit quants closer to the full-precision model.
AtomicChat/qwen36-27b-MLX-4bit and hit Use this model.mlx_lm.generate --model AtomicChat/qwen36-27b-MLX-4bit --prompt "Hello" --max-tokens 512mlx_lm.server --model AtomicChat/qwen36-27b-MLX-4bit --port 8080Qwen's recommended sampling configuration for Qwen/Qwen3.6-27B.
Qwen/Qwen3.6-27B (original weights).mlx_lm.convert on our pipeline.Original model by Qwen, released under the Apache 2.0 license. Full terms: Apache 2.0. Quantized by Atomic Chat.