Sign up

AtomicChat/gemma-4-E2B-it-MLX-8bit

🤗 On Hugging Facetext-generationapache-2.05.1B params10 GBsafetensors✓ HF checksums availableupdated today
Magnet

Base model: google/gemma-4-E2B-it

Gemma 4 E2B, 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.

Highlights

  • 2.3B effective (5.1B with embeddings) parameters: the weights this repo quantizes.
  • Context length: 128K tokens, as published by Google.
  • 35 layers: Dense decoder, hybrid sliding-window (512) and global attention.
  • Modalities: Text, Image, Audio.
  • Full imatrix ladder: every quant is calibrated with an importance matrix.
  • Reasoning: All models in the family are designed as highly capable reasoners, with configurable thinking modes.
  • Diverse & Efficient Architectures: Offers Dense and Mixture-of-Experts (MoE) variants of different sizes for scalable deployment.
[!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.

Model Overview

| Property | Value |

|---|---|

| Base model | google/gemma-4-E2B-it |

| Parameters | 2.3B effective (5.1B with embeddings) |

| Layers | 35 |

| Sliding window | 512 tokens |

| Context length | 128K tokens |

| Vocabulary | 262K |

| Modalities | Text, Image, Audio |

| Architecture | Dense decoder, hybrid sliding-window (512) and global attention, 8 attention heads over 1 KV head, Gemma4ForConditionalGeneration |

| This repo | MLX weights |

Benchmarks

| Benchmark | Score |

|---|---|

| MMLU Pro | 60.0% |

| AIME 2026 no tools | 37.5% |

| LiveCodeBench v6 | 44.0% |

| Codeforces ELO | 633 |

| GPQA Diamond | 43.4% |

| Tau2 (average over 3) | 24.5% |

| BigBench Extra Hard | 21.9% |

| MMMLU | 67.4% |

| MMMU Pro | 44.2% |

| OmniDocBench 1.5 (average edit distance, lower is better) | 0.290 |

| MATH-Vision | 52.4% |

| MedXPertQA MM | 23.5% |

| CoVoST | 33.47 |

| FLEURS (lower is better) | 0.09 |

| MRCR v2 8 needle 128k (average) | 19.1% |

Scores are Google's published results for the base google/gemma-4-E2B-it, not our own measurements. Quantization preserves the large majority of this; Q4_K_M and up stay close to full precision.

Get started

  • Atomic Chat: search AtomicChat/gemma-4-E2B-it-MLX-8bit and hit Use this model.
  • mlx-lm: mlx_lm.generate --model AtomicChat/gemma-4-E2B-it-MLX-8bit --prompt "Hello" --max-tokens 512
  • Server: mlx_lm.server --model AtomicChat/gemma-4-E2B-it-MLX-8bit --port 8080

Best practices

| Parameter | Value |

|---|---|

| temperature | 1.0 |

| top_p | 0.95 |

| top_k | 64 |

Google's recommended sampling configuration for google/gemma-4-E2B-it.

How these were made

1. Download google/gemma-4-E2B-it (original weights).

2. Convert and quantize with mlx_lm.convert on our pipeline.

License

Original model by Google, released under the Apache 2.0 license. Full terms: Apache 2.0. Quantized by Atomic Chat.