Gemma 4 E4B
, self-quantized to NVFP4 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
4.5B effective (8B with embeddings) parameters
: the weights this repo quantizes.
Context length
: 128K tokens, as published by Google.
42 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.
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
Property
Value
Base model
google/gemma-4-E4B-it
Parameters
4.5B effective (8B with embeddings)
Layers
42
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 2 KV heads,
Gemma4ForConditionalGeneration
This repo
NVFP4 weights
Benchmarks
Benchmark
Score
MMLU Pro
69.4%
AIME 2026 no tools
42.5%
LiveCodeBench v6
52.0%
Codeforces ELO
940
GPQA Diamond
58.6%
Tau2 (average over 3)
42.2%
BigBench Extra Hard
33.1%
MMMLU
76.6%
MMMU Pro
52.6%
OmniDocBench 1.5 (average edit distance, lower is better)
0.181
MATH-Vision
59.5%
MedXPertQA MM
28.7%
CoVoST
35.54
FLEURS (lower is better)
0.08
MRCR v2 8 needle 128k (average)
25.4%
Scores are Google's published results for the base
google/gemma-4-E4B-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-E4B-it-NVFP4
and hit
Use this model
.
gemma-4-E4B-it-NVFP4 huggingface.co is an AI model on huggingface.co that provides gemma-4-E4B-it-NVFP4's model effect (), which can be used instantly with this AtomicChat gemma-4-E4B-it-NVFP4 model. huggingface.co supports a free trial of the gemma-4-E4B-it-NVFP4 model, and also provides paid use of the gemma-4-E4B-it-NVFP4. Support call gemma-4-E4B-it-NVFP4 model through api, including Node.js, Python, http.
gemma-4-E4B-it-NVFP4 huggingface.co is an online trial and call api platform, which integrates gemma-4-E4B-it-NVFP4's modeling effects, including api services, and provides a free online trial of gemma-4-E4B-it-NVFP4, you can try gemma-4-E4B-it-NVFP4 online for free by clicking the link below.
AtomicChat gemma-4-E4B-it-NVFP4 online free url in huggingface.co:
gemma-4-E4B-it-NVFP4 is an open source model from GitHub that offers a free installation service, and any user can find gemma-4-E4B-it-NVFP4 on GitHub to install. At the same time, huggingface.co provides the effect of gemma-4-E4B-it-NVFP4 install, users can directly use gemma-4-E4B-it-NVFP4 installed effect in huggingface.co for debugging and trial. It also supports api for free installation.
gemma-4-E4B-it-NVFP4 install url in huggingface.co: