NexaAI / gemma-3-4b-it-8bit-MLX

huggingface.co
Total runs: 57
24-hour runs: 0
7-day runs: -15
30-day runs: -179
Model's Last Updated: July 22 2025
image-text-to-text

Introduction of gemma-3-4b-it-8bit-MLX

Model Details of gemma-3-4b-it-8bit-MLX

NexaAI/gemma-3-4b-it-8bit-MLX

Quickstart

Run them directly with nexa-sdk installed In nexa-sdk CLI:

NexaAI/gemma-3-4b-it-8bit-MLX
Overview

Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models. Gemma 3 models are multimodal, handling text and image input and generating text output, with open weights for both pre-trained variants and instruction-tuned variants. Gemma 3 has a large, 128K context window, multilingual support in over 140 languages, and is available in more sizes than previous versions. Gemma 3 models are well-suited for a variety of text generation and image understanding tasks, including question answering, summarization, and reasoning. Their relatively small size makes it possible to deploy them in environments with limited resources such as laptops, desktops or your own cloud infrastructure, democratizing access to state of the art AI models and helping foster innovation for everyone.

Inputs and outputs
  • Input:
    • Text string, such as a question, a prompt, or a document to be summarized
    • Images, normalized to 896 x 896 resolution and encoded to 256 tokens each
    • Total input context of 128K tokens for the 4B, 12B, and 27B sizes, and 32K tokens for the 1B size
  • Output:
    • Generated text in response to the input, such as an answer to a question, analysis of image content, or a summary of a document
    • Total output context of 8192 tokens
Benchmark Results

These models were evaluated against a large collection of different datasets and metrics to cover different aspects of text generation:

Reasoning and factuality
Benchmark Metric Gemma 3 PT 1B Gemma 3 PT 4B Gemma 3 PT 12B Gemma 3 PT 27B
HellaSwag 10-shot 62.3 77.2 84.2 85.6
BoolQ 0-shot 63.2 72.3 78.8 82.4
PIQA 0-shot 73.8 79.6 81.8 83.3
SocialIQA 0-shot 48.9 51.9 53.4 54.9
TriviaQA 5-shot 39.8 65.8 78.2 85.5
Natural Questions 5-shot 9.48 20.0 31.4 36.1
ARC-c 25-shot 38.4 56.2 68.9 70.6
ARC-e 0-shot 73.0 82.4 88.3 89.0
WinoGrande 5-shot 58.2 64.7 74.3 78.8
BIG-Bench Hard few-shot 28.4 50.9 72.6 77.7
DROP 1-shot 42.4 60.1 72.2 77.2
STEM and code
Benchmark Metric Gemma 3 PT 4B Gemma 3 PT 12B Gemma 3 PT 27B
MMLU 5-shot 59.6 74.5 78.6
MMLU (Pro COT) 5-shot 29.2 45.3 52.2
AGIEval 3-5-shot 42.1 57.4 66.2
MATH 4-shot 24.2 43.3 50.0
GSM8K 8-shot 38.4 71.0 82.6
GPQA 5-shot 15.0 25.4 24.3
MBPP 3-shot 46.0 60.4 65.6
HumanEval 0-shot 36.0 45.7 48.8
Multilingual
Benchmark Gemma 3 PT 1B Gemma 3 PT 4B Gemma 3 PT 12B Gemma 3 PT 27B
MGSM 2.04 34.7 64.3 74.3
Global-MMLU-Lite 24.9 57.0 69.4 75.7
WMT24++ (ChrF) 36.7 48.4 53.9 55.7
FloRes 29.5 39.2 46.0 48.8
XQuAD (all) 43.9 68.0 74.5 76.8
ECLeKTic 4.69 11.0 17.2 24.4
IndicGenBench 41.4 57.2 61.7 63.4
Multimodal
Benchmark Gemma 3 PT 4B Gemma 3 PT 12B Gemma 3 PT 27B
COCOcap 102 111 116
DocVQA (val) 72.8 82.3 85.6
InfoVQA (val) 44.1 54.8 59.4
MMMU (pt) 39.2 50.3 56.1
TextVQA (val) 58.9 66.5 68.6
RealWorldQA 45.5 52.2 53.9
ReMI 27.3 38.5 44.8
AI2D 63.2 75.2 79.0
ChartQA 63.6 74.7 76.3
VQAv2 63.9 71.2 72.9
BLINK 38.0 35.9 39.6
OKVQA 51.0 58.7 60.2
TallyQA 42.5 51.8 54.3
SpatialSense VQA 50.9 60.0 59.4
CountBenchQA 26.1 17.8 68.0
Reference

Original model card : google/gemma-3-4b-it

Runs of NexaAI gemma-3-4b-it-8bit-MLX on huggingface.co

57
Total runs
0
24-hour runs
-3
3-day runs
-15
7-day runs
-179
30-day runs

More Information About gemma-3-4b-it-8bit-MLX huggingface.co Model

More gemma-3-4b-it-8bit-MLX license Visit here:

https://choosealicense.com/licenses/gemma

gemma-3-4b-it-8bit-MLX huggingface.co

gemma-3-4b-it-8bit-MLX huggingface.co is an AI model on huggingface.co that provides gemma-3-4b-it-8bit-MLX's model effect (), which can be used instantly with this NexaAI gemma-3-4b-it-8bit-MLX model. huggingface.co supports a free trial of the gemma-3-4b-it-8bit-MLX model, and also provides paid use of the gemma-3-4b-it-8bit-MLX. Support call gemma-3-4b-it-8bit-MLX model through api, including Node.js, Python, http.

gemma-3-4b-it-8bit-MLX huggingface.co Url

https://huggingface.co/NexaAI/gemma-3-4b-it-8bit-MLX

NexaAI gemma-3-4b-it-8bit-MLX online free

gemma-3-4b-it-8bit-MLX huggingface.co is an online trial and call api platform, which integrates gemma-3-4b-it-8bit-MLX's modeling effects, including api services, and provides a free online trial of gemma-3-4b-it-8bit-MLX, you can try gemma-3-4b-it-8bit-MLX online for free by clicking the link below.

NexaAI gemma-3-4b-it-8bit-MLX online free url in huggingface.co:

https://huggingface.co/NexaAI/gemma-3-4b-it-8bit-MLX

gemma-3-4b-it-8bit-MLX install

gemma-3-4b-it-8bit-MLX is an open source model from GitHub that offers a free installation service, and any user can find gemma-3-4b-it-8bit-MLX on GitHub to install. At the same time, huggingface.co provides the effect of gemma-3-4b-it-8bit-MLX install, users can directly use gemma-3-4b-it-8bit-MLX installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

gemma-3-4b-it-8bit-MLX install url in huggingface.co:

https://huggingface.co/NexaAI/gemma-3-4b-it-8bit-MLX

Url of gemma-3-4b-it-8bit-MLX

gemma-3-4b-it-8bit-MLX huggingface.co Url

Provider of gemma-3-4b-it-8bit-MLX huggingface.co

NexaAI
ORGANIZATIONS

Other API from NexaAI

huggingface.co

Total runs: 1.3K
Run Growth: -484
Growth Rate: -38.05%
Updated:August 09 2025
huggingface.co

Total runs: 793
Run Growth: -109
Growth Rate: -13.75%
Updated:August 21 2025
huggingface.co

Total runs: 634
Run Growth: -567
Growth Rate: -89.43%
Updated:November 14 2025
huggingface.co

Total runs: 556
Run Growth: -1
Growth Rate: -0.18%
Updated:May 21 2024
huggingface.co

Total runs: 486
Run Growth: 0
Growth Rate: 0.00%
Updated:July 22 2025
huggingface.co

Total runs: 258
Run Growth: -17
Growth Rate: -6.59%
Updated:September 28 2025
huggingface.co

Total runs: 155
Run Growth: 17
Growth Rate: 10.97%
Updated:November 07 2025
huggingface.co

Total runs: 74
Run Growth: 4
Growth Rate: 5.41%
Updated:July 22 2025
huggingface.co

Total runs: 58
Run Growth: 40
Growth Rate: 68.97%
Updated:December 03 2025
huggingface.co

Total runs: 54
Run Growth: -1
Growth Rate: -1.85%
Updated:May 05 2024
huggingface.co

Total runs: 52
Run Growth: 4
Growth Rate: 7.69%
Updated:January 10 2026
huggingface.co

Total runs: 37
Run Growth: 25
Growth Rate: 67.57%
Updated:January 13 2026
huggingface.co

Total runs: 23
Run Growth: 20
Growth Rate: 86.96%
Updated:November 07 2025
huggingface.co

Total runs: 16
Run Growth: -2
Growth Rate: -12.50%
Updated:September 04 2024
huggingface.co

Total runs: 14
Run Growth: 10
Growth Rate: 71.43%
Updated:October 28 2025
huggingface.co

Total runs: 13
Run Growth: 7
Growth Rate: 53.85%
Updated:December 17 2025
huggingface.co

Total runs: 10
Run Growth: 2
Growth Rate: 20.00%
Updated:January 13 2026
huggingface.co

Total runs: 5
Run Growth: 0
Growth Rate: 0.00%
Updated:December 16 2025