Built with mlx-optiq, the MLX-native toolkit to quantize, fine-tune, and serve LLMs locally on Apple Silicon, no PyTorch and no cloud. Try the Lab · All OptiQ quants · Docs
A 4-bit mixed-precision MLX quant produced by mlx-optiq, built on Google's quantization-aware-trained (QAT) Gemma-4 base. OptiQ's sensitivity-guided per-layer bit allocation is applied on top of weights that were trained to survive low-bit quantization, and it still beats a uniform 4-bit quant of the same QAT base by +1.19 Capability Score points.
This is a quant of google/gemma-4-E4B-it-qat-q4_0-unquantized. Per-layer bit-widths come from a KL-divergence sensitivity pass on a six-domain calibration mix (prose, reasoning, code, agent, tool-call, constraint-bearing instructions). Sensitive layers go to 8-bit, robust ones stay at 4-bit.
Six-metric mean (MMLU, GSM8K, IFEval, BFCL, HumanEval, HashHop), scored against the published uniform 4-bit quant of the same QAT base (mlx-community/gemma-4-E4B-it-qat-4bit). That comparison isolates what the mixed-precision allocation adds, holding the base fixed.
Benchmark
This model (OptiQ, QAT base)
Uniform-4 (QAT base)
Delta
MMLU (5-shot, 1000)
57.7%
57.4%
+0.3
GSM8K (1000)
80.0%
79.5%
+0.5
IFEval (full, strict)
69.1%
67.8%
+1.3
BFCL-V3 simple (200)
87.5%
87.5%
+0.0
HumanEval (pass@1, 164)
81.7%
78.7%
+3.0
HashHop (long-context)
36.0%
34.0%
+2.0
Capability Score (mean)
68.67
67.48
+1.19
The mixed-precision allocation adds +1.19 points over uniform 4-bit on the QAT base, with the largest gains on HumanEval and the long-context HashHop task. The mixed quant is 5.17 bits-per-weight (about 7.0 GB on disk) versus 4.0 bits-per-weight (about 6.3 GB) for uniform 4-bit: the gain comes from spending the extra budget on the layers that need it.
The same repo loads text-only under stock mlx-lm and image+text under optiq. The bf16 vision tower rides in optiq_vision.safetensors, which mlx-lm ignores (it globs model*.safetensors), so both paths work from one artifact.
This quant was produced by mlx-optiq. Point it at any Hugging Face model to get the same sensitivity-aware mixed precision:
pip install mlx-optiq
optiq convert <hf-model-id> --target-bpw 5.0 --candidate-bits 4,8
optiq lab # or open the full local workbench: chat, compare, quantize, fine-tune
import os
os.environ["HF_ENDPOINT"] = "https://freeweights.allternit.com"
from transformers import AutoModelForCausalLM, AutoTokenizer
tok = AutoTokenizer.from_pretrained("mlx-community/gemma-4-e4b-it-qat-OptiQ-4bit", revision="a78078f40a3046b66cde60ee4c564393ccc595b8")
model = AutoModelForCausalLM.from_pretrained("mlx-community/gemma-4-e4b-it-qat-OptiQ-4bit", revision="a78078f40a3046b66cde60ee4c564393ccc595b8", device_map="auto")
mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.gemmaSubject: 
