What are the hardware requirements for Granite 34B Code Base 4bit?

Granite 34B Code Base 4bit requires approximately 18.9 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Granite 34B Code Base 4bit and how large is it?

Granite 34B Code Base 4bit is developed by mlx-community, 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 4bit?

Granite 34B Code Base 4bit 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 4bit by mlx-community — VRAM 18.9GB

Name: Granite 34B Code Base 4bit
Author: mlx-community

Granite 34B Code Base 4bit is an open-source language model by mlx-community. Features: 34b LLM, VRAM: 18.9GB, License: apache-2.0, Quantized, Code Generating, LLM Explorer Score: 0.12.

4bit Code Codegen Dataset:bigcode/starcoderdata Dataset:codeparrot/github-code... Dataset:math-ai/stackmathqa Dataset:open-web-math/open-web... Endpoints compatible Gpt bigcode Granite Mlx Model-index Quantized Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/mlx-community/granite-34b-code-base-4bit

Granite 34B Code Base 4bit Parameters and Internals

Model Type

text-generation

Additional Notes

The model was converted to MLX format and can be used with mlx-lm library version 0.13.0.

Training Details

Data Sources:

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

Methodology:

Converted to MLX format using mlx-lm version 0.13.0

LLM Name	Granite 34B Code Base 4bit
Repository 🤗	https://huggingface.co/mlx-community/granite-34b-code-base-4bit
Base Model(s)	Granite 34B Code Base ibm-granite/granite-34b-code-base
Model Size	34b
Required VRAM	18.9 GB
Updated	2026-07-21
Maintainer	mlx-community
Model Type	gpt_bigcode
Model Files	5.4 GB: 1-of-4 5.3 GB: 2-of-4 5.3 GB: 3-of-4 2.9 GB: 4-of-4
Quantization Type	4bit
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 4bit 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 4bit

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 Instruct AWQ	0K / 18.6 GB	5	3
Granite 34B Code Base 8K	0K / 67.1 GB	150	20

Note: green Score (e.g. "73.2") means that the model is better than mlx-community/granite-34b-code-base-4bit.