What are the hardware requirements for CodeGemma 7B AWQ?

CodeGemma 7B AWQ requires approximately 7.2 GB of VRAM and supports a context window of 8K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed CodeGemma 7B AWQ and how large is it?

CodeGemma 7B AWQ is developed by TechxGenus, a model with 7b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does CodeGemma 7B AWQ perform on standard benchmarks?

CodeGemma 7B AWQ has the following published scores: MMLU 56.59, HumanEval (Python) 40.13. Compare against reference models on this page or on the LLM Explorer leaderboards.

CodeGemma 7B AWQ by TechxGenus — VRAM 7.2GB, 8K context

Name: CodeGemma 7B AWQ
Author: TechxGenus

CodeGemma 7B AWQ is an open-source language model by TechxGenus. Features: 7b LLM, VRAM: 7.2GB, Context: 8K, License: other, Quantized, LLM Explorer Score: 0.14, Arc: 53.9, HellaSwag: 76.7, MMLU: 56.6, GSM8K: 45.5, HumanEval: 40.1.

4-bit Awq Code Endpoints compatible Gemma Quantized Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/TechxGenus/CodeGemma-7b-AWQ

CodeGemma 7B AWQ Parameters and Internals

Model Type

text-generation, code generation

Use Cases

Areas:

text generation, code generation

Primary Use Cases:

code generation, coding-related tasks

Limitations:

Model may produce errors, misleading contents, or struggle with non-coding tasks., Limited testing, requires additional safety evaluation.

Considerations:

Additional safety testing required for real-world deployment.

Supported Languages

programming languages (Python)

Training Details

Data Sources:

Gemma-7b base model , additional 0.7 billion high-quality, code-related tokens

Data Volume:

0.7 billion high-quality tokens

Methodology:

Fine-tuned with DeepSpeed ZeRO 3 and Flash Attention 2

Training Time:

3 epochs

Safety Evaluation

Ethical Considerations:

Limited testing, additional safety testing recommended before real-world deployment.

Input Output

Input Format:

Instruction format, Alpaca instruction format (excluding system prompt)

Accepted Modalities:

text

Output Format:

text

LLM Name	CodeGemma 7B AWQ
Repository 🤗	https://huggingface.co/TechxGenus/CodeGemma-7b-AWQ
Base Model(s)	Codegemma 7B unsloth/codegemma-7b
Model Size	7b
Required VRAM	7.2 GB
Updated	2026-08-04
Maintainer	TechxGenus
Model Type	gemma
Model Files	6.6 GB: 1-of-2 0.6 GB: 2-of-2
AWQ Quantization	Yes
Quantization Type	awq
Model Architecture	GemmaForCausalLM
License	other
Context Length	8192
Model Max Length	8192
Transformers Version	4.39.0.dev0
Tokenizer Class	GemmaTokenizer
Padding Token	<eos>
Vocabulary Size	256000
Torch Data Type	float16

Rank the CodeGemma 7B AWQ capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

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

Best Alternatives to CodeGemma 7B AWQ

Best Alternatives	Context / RAM	Downloads	Likes
Gemma 1.1 7B It AWQ	8K / 7.2 GB	6	0
Codegemma 7B AWQ	8K / 7.2 GB	8	0
SeaLLM 7B V2.5 AWQ	8K / 7.2 GB	5	2
SeaLLM 7B V2.5 AWQ	8K / 5.6 GB	7	0
Gemma Ko 7B AWQ	8K / 5.6 GB	9	0
Codegemma 1.1 7B It AWQ	8K / 7.2 GB	5	0
Gemma 7B It AWQ	8K / 7.2 GB	93	2
Gemma 7B It AWQ	8K / 7.2 GB	9	0
Gemma 7B AWQ	8K / 7.2 GB	6	0
...t Cleaner Gemma 32k Merged 16b	31K / 17.1 GB	7	0

Note: green Score (e.g. "73.2") means that the model is better than TechxGenus/CodeGemma-7b-AWQ.