What are the hardware requirements for Granite 3B Code Base?

Granite 3B Code Base requires approximately 7 GB of VRAM and supports a context window of 2K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Granite 3B Code Base and how large is it?

Granite 3B Code Base is developed by ibm-granite, a model with 3b 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 Granite 3B Code Base?

Granite 3B Code Base is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Granite 3B Code Base by ibm-granite — VRAM 7GB, 2K context

Name: Granite 3B Code Base
Author: ibm-granite

Granite 3B Code Base is an open-source language model by ibm-granite. Features: 3b LLM, VRAM: 7GB, Context: 2K, License: apache-2.0, LLM Explorer Score: 0.16.

Arxiv:2405.04324 Autotrain compatible Code Dataset:bigcode/starcoderdata Dataset:codeparrot/github-code... Dataset:math-ai/stackmathqa Dataset:open-web-math/open-web... Granite Llama Model-index Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/ibm-granite/granite-3b-code-base

Granite 3B Code Base Benchmarks

LLME Score: 0.15773

^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)

Granite 3B Code Base (ibm-granite/granite-3b-code-base)

Granite 3B Code Base Parameters and Internals

Model Type

decoder-only, text generation

Use Cases

Areas:

software engineering productivity

Applications:

code generation, code explanation, code fixing, generating unit tests, generating documentation, addressing technical debt issues, vulnerability detection, code translation

Limitations:

Generated code is not guaranteed to work as intended., Has not undergone any safety alignment.

Considerations:

Caution against complete reliance for crucial decisions.

Additional Notes

The model is trained from scratch with a two-phase training strategy.

Supported Languages

proficiency (unknown), languages_supported (116 programming languages)

Training Details

Data Sources:

codeparrot/github-code-clean, bigcode/starcoderdata

Methodology:

Two-phase training strategy

Hardware Used:

IBM's super computing clusters, namely Vela and Blue Vela, outfitted with NVIDIA A100 and H100 GPUs

Model Architecture:

Decoder-only

Responsible Ai Considerations

Mitigation Strategies:

HAP, PII, Malware Filtering and deduplication strategies to reduce risks.

LLM Name	Granite 3B Code Base
Repository 🤗	https://huggingface.co/ibm-granite/granite-3b-code-base
Model Size	3b
Required VRAM	7 GB
Updated	2024-09-01
Maintainer	ibm-granite
Model Type	llama
Model Files	5.0 GB: 1-of-2 2.0 GB: 2-of-2
Model Architecture	LlamaForCausalLM
License	apache-2.0
Context Length	2048
Model Max Length	2048
Transformers Version	4.41.0.dev0
Tokenizer Class	GPT2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	49152
Torch Data Type	bfloat16

Quantized Models of the Granite 3B Code Base

Model	Likes	Downloads	VRAM
Granite 3B Code Instruct GGUF	1	926	1 GB

Best Alternatives to Granite 3B Code Base

Best Alternatives	Context / RAM	Downloads	Likes
Nanbeige4.1 3B	256K / 7.9 GB	11138	1142
Nanbeige4.1 3B Heretic	256K / 7.9 GB	149	50
Nanbeige4.1 3B Bf16	256K / 7.9 GB	47	3
Nanbeige4.1 3B Heretic Mxfp4	256K / 7.9 GB	34	2
Nanbeige4.1 3B Heretic	256K / 7.9 GB	4	1
Nanbeige4.1 3B Heretic	256K / 7.9 GB	7	0
ISA 03 Mini 3B Hybrid Preview	256K / 6.5 GB	4	4
Llama 3.2 3B Instruct	128K / 6.5 GB	1829572	2368
G9v3 3B	128K / 6 GB	214	13
Llama 3.2 3B	128K / 6.5 GB	706937	845

Note: green Score (e.g. "73.2") means that the model is better than ibm-granite/granite-3b-code-base.

Rank the Granite 3B Code Base 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? 55556 in total.

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

Our Social Media →

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

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

Release v20260328a

Support LLM Explorer

Granite 3B Code Base by ibm-granite