What are the hardware requirements for Gemma 4 A4B 98e V5 Coder It?

Gemma 4 A4B 98e V5 Coder It requires approximately 41 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Gemma 4 A4B 98e V5 Coder It and how large is it?

Gemma 4 A4B 98e V5 Coder It is developed by ManniX-ITA, a model with 20.5b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Gemma 4 A4B 98e V5 Coder It?

Gemma 4 A4B 98e V5 Coder It is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Gemma 4 A4B 98e V5 Coder It by ManniX-ITA — VRAM 41GB

Name: Gemma 4 A4B 98e V5 Coder It
Author: ManniX-ITA

Gemma 4 A4B 98e V5 Coder It is an open-source language model by ManniX-ITA. Features: 20.5b LLM, VRAM: 41GB, License: gemma, Code Generating, LLM Explorer Score: 0.28.

Arxiv:2405.04324 Arxiv:2406.11931 Arxiv:2409.12186 Arxiv:2412.08905 Base model:finetune:mannix-ita... Base model:mannix-ita/gemma-4-... Code Codegen Expert-pruning Gemma4 Moe Omnimergekit Region:us Safetensors Sharded Surgery Tensorflow

Model Card on HF 🤗: https://huggingface.co/ManniX-ITA/gemma-4-A4B-98e-v5-coder-it

Gemma 4 A4B 98e V5 Coder It Benchmarks

LLME Score: 0.28117

^nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

What is the LLM Explorer Rank (Score)

Gemma 4 A4B 98e V5 Coder It (ManniX-ITA/gemma-4-A4B-98e-v5-coder-it)

🌟 Advertise your project 🚀

Gemma 4 A4B 98e V5 Coder It Parameters and Internals

LLM Name	Gemma 4 A4B 98e V5 Coder It
Repository 🤗	https://huggingface.co/ManniX-ITA/gemma-4-A4B-98e-v5-coder-it
Base Model(s)	ManniX-ITA/gemma-4-A4B-98e-v4-it ManniX-ITA/gemma-4-A4B-98e-v4-it
Model Size	20.5b
Required VRAM	41 GB
Updated	2026-05-19
Maintainer	ManniX-ITA
Model Type	gemma4
Model Files	5.3 GB: 1-of-9 5.1 GB: 2-of-9 5.1 GB: 3-of-9 5.1 GB: 4-of-9 4.7 GB: 5-of-9 4.7 GB: 6-of-9 5.1 GB: 7-of-9 5.0 GB: 8-of-9 0.9 GB: 9-of-9
Generates Code	Yes
Model Architecture	Gemma4ForConditionalGeneration
License	gemma
Transformers Version	5.5.0.dev0
Tokenizer Class	GemmaTokenizer
Padding Token	<pad>

Rank the Gemma 4 A4B 98e V5 Coder It Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

What open-source LLMs or SLMs are you in search of? 53834 in total.

Email us: info@extractum.io. Our Privacy Policy | Terms and Conditions | Suggest an improvement.

Our Social Media →

Original data from HuggingFace, OpenCompass and various public git repos.

Check out Ag3ntum — our secure, self-hosted AI agent for server management.

Release v20260328a

Support LLM Explorer

Gemma 4 A4B 98e V5 Coder It by ManniX-ITA

» All LLMs » ManniX-ITA » Gemma 4 A4B 98e V5 Coder It URL Share it on

Gemma 4 A4B 98e V5 Coder It Benchmarks

Gemma 4 A4B 98e V5 Coder It Parameters and Internals

Rank the Gemma 4 A4B 98e V5 Coder It Capabilities

What open-source LLMs or SLMs are you in search of? 53834 in total.