AtomicChat

gemma-4-12B-it-NVFP4

README

License: apache-2.0

Highlights

11.95B parameters: the weights this repo quantizes.
Context length: 256K tokens, as published by Google.
48 layers: Dense decoder, hybrid sliding-window (1024) 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 NVFP4s 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

Table with columns: Property, Value
Property	Value
Base model	`google/gemma-4-12B-it`
Parameters	11.95B
Layers	48
Sliding window	1024 tokens
Context length	256K tokens
Vocabulary	262K
Modalities	Text, Image, Audio
Architecture	Dense decoder, hybrid sliding-window (1024) and global attention, 16 attention heads over 8 KV heads, `Gemma4UnifiedForConditionalGeneration`
This repo	NVFP4 weights

Benchmarks

Table with columns: Benchmark, Score
Benchmark	Score
MMLU Pro	77.2%
AIME 2026 no tools	77.5%
LiveCodeBench v6	72.0%
Codeforces ELO	1659
GPQA Diamond	78.8%
Tau2 (average over 3)	69.0%
HLE no tools	5.2%
BigBench Extra Hard	53.0%
MMMLU	83.4%

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.

Get started

Atomic Chat: search AtomicChat/gemma-4-12B-it-NVFP4 and hit Use this model.
vLLM: vllm serve AtomicChat/gemma-4-12B-it-NVFP4 --max-model-len 8192

Best practices

Table with columns: Parameter, Value
Parameter	Value
temperature	1.0
top_p	0.95
top_k	64

Google's recommended sampling configuration for google/gemma-4-12B-it.

How these were made

Download google/gemma-4-12B-it (original weights).
Quantize to NVFP4 with llm-compressor over a calibration corpus.

License

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

Available on FriendliAI

Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Learn more

Model Details

Model Provider

AtomicChat

Model Tree

Base

google/gemma-4-12B-it

Quantized

this model

Input Modalities

TextAudioImageVideo

Output Modalities

Text

Supported Functionality