What are the hardware requirements for Google Codegemma 2B AWQ 4bit Smashed?

Google Codegemma 2B AWQ 4bit Smashed requires approximately 3.1 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 Google Codegemma 2B AWQ 4bit Smashed and how large is it?

Google Codegemma 2B AWQ 4bit Smashed is developed by PrunaAI, a model with 2b 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 Google Codegemma 2B AWQ 4bit Smashed?

Google Codegemma 2B AWQ 4bit Smashed is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Google Codegemma 2B AWQ 4bit Smashed by PrunaAI — VRAM 3.1GB, 8K context

Name: Google Codegemma 2B AWQ 4bit Smashed
Author: PrunaAI

Google Codegemma 2B AWQ 4bit Smashed is an open-source language model by PrunaAI. Features: 2b LLM, VRAM: 3.1GB, Context: 8K, Quantized, LLM Explorer Score: 0.12.

4-bit 4bit Awq Base model:google/codegemma-2b Base model:quantized:google/co... Gemma Pruna-ai Quantized Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/PrunaAI/google-codegemma-2b-AWQ-4bit-smashed

Google Codegemma 2B AWQ 4bit Smashed Parameters and Internals

Model Type

text generation

Use Cases

Areas:

research, commercial applications

Considerations:

Efficiency results may vary depending on settings, recommend testing in use-case conditions.

Additional Notes

PrunaAI offers to compress models to be cheaper, smaller, faster, and greener.

Input Output

Input Format:

Text prompt.

Accepted Modalities:

text

Output Format:

Text output.

Performance Tips:

Metrics like memory and speed may vary by settings like hardware and batch size. Recommend testing in specific use-case conditions.

LLM Name	Google Codegemma 2B AWQ 4bit Smashed
Repository 🤗	https://huggingface.co/PrunaAI/google-codegemma-2b-AWQ-4bit-smashed
Base Model(s)	Codegemma 2B google/codegemma-2b
Model Size	2b
Required VRAM	3.1 GB
Updated	2025-09-23
Maintainer	PrunaAI
Model Type	gemma
Model Files	3.1 GB
AWQ Quantization	Yes
Quantization Type	awq\|4bit
Model Architecture	GemmaForCausalLM
Context Length	8192
Model Max Length	8192
Transformers Version	4.42.4
Tokenizer Class	GemmaTokenizer
Padding Token	<pad>
Vocabulary Size	256000
Torch Data Type	float16

Rank the Google Codegemma 2B AWQ 4bit Smashed 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 Google Codegemma 2B AWQ 4bit Smashed

Best Alternatives	Context / RAM	Downloads	Likes
Codegemma 1.1 2B AWQ	8K / 3.1 GB	12	0
Gemma 1.1 2B It AWQ	8K / 3.1 GB	4	1
Gemma 2B It AWQ	8K / 3.1 GB	95	0
Gemma 2B AWQ	8K / 3.1 GB	14	0
... 2B It Hermes Function Calling	8K / 5.1 GB	18	0
Octopus V2 Gguf AWQ	8K / 1.2 GB	2356	7
Octopus V2 Gguf AWQ	8K / 1.2 GB	1577	7
Vi Gemma 2B RAG	8K / 5.1 GB	36	13
My AwesomeFinance Model	8K / 2.1 GB	7	0
... 2.8 Gemma 2B HQQ 1bit Smashed	8K / 1.3 GB	5	0

Note: green Score (e.g. "73.2") means that the model is better than PrunaAI/google-codegemma-2b-AWQ-4bit-smashed.