No official torrent yet — requesting it tells the flock what to host next. You cannot seed a catalog-only page.
Cataloged from AtomicChat/gemma-4-12B-it-MLX-4bit
All models by AtomicChat →
Gemma 4 12B, self-quantized to MLX by Atomic Chat. Built straight from Google'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.
Scores are Google's published results for the base google/gemma-4-12B-it, not our own measurements. Quantization preserves the large majority of this; Q4_K_M and up stay close to full precision.
AtomicChat/gemma-4-12b-it-MLX-4bit and hit Use this model.mlx_lm.generate --model AtomicChat/gemma-4-12b-it-MLX-4bit --prompt "Hello" --max-tokens 512mlx_lm.server --model AtomicChat/gemma-4-12b-it-MLX-4bit --port 8080Google's recommended sampling configuration for google/gemma-4-12B-it.
google/gemma-4-12B-it (original weights).mlx_lm.convert on our pipeline.Original model by Google, released under the Apache 2.0 license. Full terms: Apache 2.0. Quantized by Atomic Chat.