What are the hardware requirements for Granite 20B Code Base FP8?

Granite 20B Code Base FP8 requires approximately 20.4 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Granite 20B Code Base FP8 and how large is it?

Granite 20B Code Base FP8 is developed by nm-testing, a model with 20b 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 20B Code Base FP8?

Granite 20B Code Base FP8 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Granite 20B Code Base FP8 by nm-testing — VRAM 20.4GB

Name: Granite 20B Code Base FP8
Author: nm-testing

Granite 20B Code Base FP8 is an open-source language model by nm-testing. Features: 20b LLM, VRAM: 20.4GB, Code Generating, LLM Explorer Score: 0.13.

Autotrain compatible Codegen Endpoints compatible Fp8 Gpt bigcode Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/nm-testing/granite-20b-code-base-FP8

Granite 20B Code Base FP8 Parameters and Internals

Model Type

Causal Language Model, Quantized

Additional Notes

Quantized using AutoFP8 with FP8 method and static activation scheme.

Input Output

Input Format:

Tokenized inputs as PyTorch tensors.

Accepted Modalities:

text

Output Format:

Quantized model parameters in FP8 format.

LLM Name	Granite 20B Code Base FP8
Repository 🤗	https://huggingface.co/nm-testing/granite-20b-code-base-FP8
Model Size	20b
Required VRAM	20.4 GB
Updated	2025-09-23
Maintainer	nm-testing
Model Type	gpt_bigcode
Model Files	5.0 GB: 1-of-5 4.9 GB: 2-of-5 4.9 GB: 3-of-5 4.9 GB: 4-of-5 0.7 GB: 5-of-5
Generates Code	Yes
Model Architecture	GPTBigCodeForCausalLM
Model Max Length	9223372036854775807
Transformers Version	4.41.2
Tokenizer Class	GPT2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	49152
Torch Data Type	bfloat16
Activation Function	gelu_pytorch_tanh

Rank the Granite 20B Code Base FP8 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 20B Code Base FP8

Best Alternatives	Context / RAM	Downloads	Likes
Granite 20B Code Instruct 8K	0K / 40 GB	9754	43
Granite 20B Code Instruct	0K / 40 GB	10209	30
Granite 20B Code Base	0K / 40 GB	2250	12
Granite 20B Functioncalling	0K / 40 GB	210	36
Granite 20B Code Base 8K	0K / 40 GB	1221	14
Granite 20B Code Instruct R1.1	0K / 40 GB	37	1
Granite 20B Code Base R1.1	0K / 40 GB	23	2
Granite 20B Code Base GGUF	0K / 12.8 GB	27	0

Note: green Score (e.g. "73.2") means that the model is better than nm-testing/granite-20b-code-base-FP8.