What are the hardware requirements for Gla 2.7B 100B?

Gla 2.7B 100B requires approximately 5.4 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 Gla 2.7B 100B and how large is it?

Gla 2.7B 100B is developed by fla-hub, a model with 100b 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 Gla 2.7B 100B?

Gla 2.7B 100B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Gla 2.7B 100B by fla-hub — VRAM 5.4GB, 2K context

Name: Gla 2.7B 100B
Author: fla-hub

Gla 2.7B 100B is an open-source language model by fla-hub. Features: 100b LLM, VRAM: 5.4GB, Context: 2K, LLM Explorer Score: 0.14.

Arxiv:1910.09700 Endpoints compatible Gla Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/fla-hub/gla-2.7B-100B

Gla 2.7B 100B Parameters and Internals

LLM Name	Gla 2.7B 100B
Repository 🤗	https://huggingface.co/fla-hub/gla-2.7B-100B
Model Size	100b
Required VRAM	5.4 GB
Updated	2026-08-04
Maintainer	fla-hub
Model Type	gla
Model Files	5.0 GB: 1-of-2 0.4 GB: 2-of-2
Model Architecture	GLAForCausalLM
Context Length	2048
Model Max Length	2048
Transformers Version	4.48.2
Tokenizer Class	LlamaTokenizer
Vocabulary Size	32000
Torch Data Type	bfloat16

Rank the Gla 2.7B 100B 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 Gla 2.7B 100B

Best Alternatives	Context / RAM	Downloads	Likes
Gla 1.3B 100B	2K / 2.7 GB	4191	1

Note: green Score (e.g. "73.2") means that the model is better than fla-hub/gla-2.7B-100B.