Gemma 4 MLX Quantizations - a DreamFoundries Collection

DreamFoundries 's Collections

K2 Horizon MLX Quants

Qwen3.8 MLX Quants

Laguna S 2.1 MLX Quantizations

Qwen AgentWorld MLX Quantizations

Agents A1 MLX Quantizations

SuperQwen AgentWorld MLX Quantizations

SuperGemma4 MLX Quantizations

Nemotron 3 MLX Quantizations

Qwen 3.6 MLX Quantizations

Qwen 3.5 MLX Quantizations

Gemma 4 MLX Quantizations

updated Aug 25

MLX-LM affine quantizations for Gemma4; see each model card for details. · Get MLXHub: mlxhub.app

Upvote

DreamFoundries/gemma-4-E2B-it-4bit

Text Generation • 5B • Updated Aug 25 • 255

Note 4-bit MLX-LM affine quantization of google/gemma-4-E2B-it. No comparative benchmarks yet.
DreamFoundries/gemma-4-31B-it-4bit

Text Generation • 31B • Updated Aug 25 • 36

Note 4-bit MLX-LM affine quantization of google/gemma-4-31B-it. No comparative benchmarks yet.
DreamFoundries/gemma-4-31B-it-6bit

Text Generation • 31B • Updated Aug 25 • 65

Note 6-bit MLX-LM affine quantization of google/gemma-4-31B-it. No comparative benchmarks yet.
DreamFoundries/gemma-4-31B-it-8bit

Text Generation • 31B • Updated Aug 25 • 35

Note 8-bit MLX-LM affine quantization of google/gemma-4-31B-it. No comparative benchmarks yet.
DreamFoundries/gemma-4-26B-A4B-it-4bit

Text Generation • 25B • Updated Aug 25 • 39

Note 4-bit MLX-LM affine quantization of google/gemma-4-26B-A4B-it. No comparative benchmarks yet.
DreamFoundries/gemma-4-26B-A4B-it-6bit

Text Generation • 25B • Updated Aug 25 • 78

Note 6-bit MLX-LM affine quantization of google/gemma-4-26B-A4B-it. No comparative benchmarks yet.
DreamFoundries/gemma-4-26B-A4B-it-8bit

Text Generation • 25B • Updated Aug 25 • 69

Note 8-bit MLX-LM affine quantization of google/gemma-4-26B-A4B-it. No comparative benchmarks yet.
DreamFoundries/gemma-4-12B-it-4bit

Text Generation • 12B • Updated Aug 25 • 75

Note 4-bit MLX-LM affine quantization of google/gemma-4-12B-it. No comparative benchmarks yet.
DreamFoundries/gemma-4-12B-it-6bit

Text Generation • 12B • Updated Aug 25 • 109

Note 6-bit MLX-LM affine quantization of google/gemma-4-12B-it. No comparative benchmarks yet.
DreamFoundries/gemma-4-12B-it-8bit

Text Generation • 12B • Updated Aug 25 • 70

Note 8-bit MLX-LM affine quantization of google/gemma-4-12B-it. No comparative benchmarks yet.
DreamFoundries/gemma-4-E4B-it-4bit

Text Generation • 7B • Updated Aug 25 • 177

Note 4-bit MLX-LM affine quantization of google/gemma-4-E4B-it. No comparative benchmarks yet.
DreamFoundries/gemma-4-E4B-it-6bit

Text Generation • 7B • Updated Aug 25 • 76

Note 6-bit MLX-LM affine quantization of google/gemma-4-E4B-it. No comparative benchmarks yet.
DreamFoundries/gemma-4-E4B-it-8bit

Text Generation • 7B • Updated Aug 25 • 195 • 1

Note 8-bit MLX-LM affine quantization of google/gemma-4-E4B-it. No comparative benchmarks yet.
DreamFoundries/gemma-4-E2B-it-6bit

Text Generation • 5B • Updated Aug 25 • 106

Note 6-bit MLX-LM affine quantization of google/gemma-4-E2B-it. No comparative benchmarks yet.
DreamFoundries/gemma-4-E2B-it-8bit

Text Generation • 5B • Updated Aug 25 • 33

Note 8-bit MLX-LM affine quantization of google/gemma-4-E2B-it. No comparative benchmarks yet.

Upvote