You can deploy this model and start earning money today!

AtomicChat/
gemma-4-26B-A4B-it-MLX-8bit

Name: gemma-4-26B-A4B-it-MLX-8bit
Availability: InStock

google/gemma-4-26B-A4B-it

quantized

apache-2.0

8-bit

Views

No views yet

Base model: google/gemma-4-26B-A4B-it

Gemma 4 26B A4B, 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

25.2B total / 3.8B active per token parameters: the weights this repo quantizes.
Context length: 256K tokens, as published by Google.
30 layers: Mixture-of-Experts, hybrid sliding-window (1024) and global attention.
Modalities: Text, Image.
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-4-26B-A4B-it`
Parameters	25.2B total / 3.8B active per token
Layers	30
Experts	128 routed (top-8)
Sliding window	1024 tokens
Context length	256K tokens
Vocabulary	262K
Modalities	Text, Image
Architecture	Mixture-of-Experts, 128 experts (top-8), hybrid sliding-window (1024) and global attention, 16 attention heads over 8 KV heads, `Gemma4ForConditionalGeneration`
This repo	MLX weights

Benchmarks

Benchmark	Score
MMLU Pro	82.6%
AIME 2026 no tools	88.3%
LiveCodeBench v6	77.1%
Codeforces ELO	1718
GPQA Diamond	82.3%
Tau2 (average over 3)	68.2%
HLE no tools	8.7%
HLE with search	17.2%
BigBench Extra Hard	64.8%
MMMLU	86.3%
MMMU Pro	73.8%
OmniDocBench 1.5 (average edit distance, lower is better)	0.149
MATH-Vision	82.4%
MedXPertQA MM	58.1%
MRCR v2 8 needle 128k (average)	44.1%

Scores are Google's published results for the base google/gemma-4-26B-A4B-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-4-26B-A4B-it-MLX-8bit and hit Use this model.
mlx-lm: mlx_lm.generate --model AtomicChat/gemma-4-26B-A4B-it-MLX-8bit --prompt "Hello" --max-tokens 512
Server: mlx_lm.server --model AtomicChat/gemma-4-26B-A4B-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-4-26B-A4B-it.

How these were made

Download google/gemma-4-26B-A4B-it (original weights).
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.

AtomicChat/gemma-4-26B-A4B-it-MLX-8bit