What are the hardware requirements for Granite 34B Code Base 8K?

Granite 34B Code Base 8K requires approximately 67.1 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Granite 34B Code Base 8K and how large is it?

Granite 34B Code Base 8K is developed by ibm-granite, a model with 34b 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 34B Code Base 8K?

Granite 34B Code Base 8K is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Granite 34B Code Base 8K by ibm-granite — VRAM 67.1GB

Name: Granite 34B Code Base 8K
Author: ibm-granite

Granite 34B Code Base 8K is an open-source language model by ibm-granite. Features: 34b LLM, VRAM: 67.1GB, License: apache-2.0, Code Generating, LLM Explorer Score: 0.12.

Arxiv:2405.04324 Code Codegen Dataset:bigcode/starcoderdata Dataset:codeparrot/github-code... Dataset:math-ai/stackmathqa Dataset:open-web-math/open-web... Endpoints compatible Ext 8k Gpt bigcode Granite Model-index Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/ibm-granite/granite-34b-code-base-8k

Granite 34B Code Base 8K Parameters and Internals

Model Type

code generation

Use Cases

Primary Use Cases:

Code generation, Code explanation, Code fixing

Training Details

Data Sources:

codeparrot/github-code-clean, bigcode/starcoderdata, open-web-math/open-web-math, math-ai/StackMathQA

Data Volume:

3 trillion tokens in phase 1, 500 billion tokens in phase 2

Methodology:

Depth upscaling

Hardware Used:

NVIDIA A100 GPUs, NVIDIA H100 GPUs

Model Architecture:

Decoder-only

LLM Name	Granite 34B Code Base 8K
Repository 🤗	https://huggingface.co/ibm-granite/granite-34b-code-base-8k
Model Size	34b
Required VRAM	67.1 GB
Updated	2026-08-03
Maintainer	ibm-granite
Model Type	gpt_bigcode
Model Files	5.0 GB: 1-of-14 4.9 GB: 2-of-14 4.9 GB: 3-of-14 4.9 GB: 4-of-14 4.9 GB: 5-of-14 4.9 GB: 6-of-14 4.9 GB: 7-of-14 4.9 GB: 8-of-14 4.9 GB: 9-of-14 4.9 GB: 10-of-14 4.9 GB: 11-of-14 4.9 GB: 12-of-14 4.9 GB: 13-of-14 3.3 GB: 14-of-14
Context Length	8k
Generates Code	Yes
Model Architecture	GPTBigCodeForCausalLM
License	apache-2.0
Model Max Length	8192
Transformers Version	4.38.1
Tokenizer Class	GPT2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	49152
Torch Data Type	bfloat16
Activation Function	gelu_pytorch_tanh

Rank the Granite 34B Code Base 8K 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 Granite 34B Code Base 8K

Best Alternatives	Context / RAM	Downloads	Likes
Granite 34B Code Instruct	0K / 67.1 GB	2710	68
Granite 34B Code Instruct 8K	0K / 67.1 GB	574	78
Granite 34B Code Base	0K / 67.1 GB	505	17
Granite 34B Code Base 4bit	0K / 18.9 GB	11	1
Granite 34B Code Instruct AWQ	0K / 18.6 GB	5	3

Note: green Score (e.g. "73.2") means that the model is better than ibm-granite/granite-34b-code-base-8k.