What are the hardware requirements for TW3 JRGL V2?

TW3 JRGL V2 requires approximately 79.7 GB of VRAM and supports a context window of 32K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed TW3 JRGL V2 and how large is it?

TW3 JRGL V2 is developed by paloalma, a model with 72b 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 TW3 JRGL V2?

TW3 JRGL V2 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

TW3 JRGL V2 by paloalma — VRAM 79.7GB, 32K context

Name: TW3 JRGL V2
Author: paloalma

TW3 JRGL V2 is an open-source language model by paloalma. Features: 72b LLM, VRAM: 79.7GB, Context: 32K, License: apache-2.0, Merged, LLM Explorer Score: 0.25.

Merged Model Davidkim205/rhea-72b-v0.5 Endpoints compatible Llama Mtsair/multiverse 70b Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/paloalma/TW3-JRGL-v2

TW3 JRGL V2 Parameters and Internals

Additional Notes

This model was developed under the supervision of Andre-Louis Rochet and Paul Lemaistre. It was sponsored by ECE engineering school and RunPod.

LLM Name	TW3 JRGL V2
Repository 🤗	https://huggingface.co/paloalma/TW3-JRGL-v2
Merged Model	Yes
Model Size	72b
Required VRAM	79.7 GB
Updated	2026-05-13
Maintainer	paloalma
Model Type	llama
Model Files	1.9 GB: 1-of-82 0.4 GB: 2-of-82 2.5 GB: 3-of-82 1.9 GB: 4-of-82 1.9 GB: 5-of-82 1.6 GB: 6-of-82 1.7 GB: 7-of-82 1.7 GB: 8-of-82 1.9 GB: 9-of-82 1.9 GB: 10-of-82 1.9 GB: 11-of-82 1.6 GB: 12-of-82 1.7 GB: 13-of-82 1.9 GB: 14-of-82 1.9 GB: 15-of-82 1.9 GB: 16-of-82 1.6 GB: 17-of-82 1.7 GB: 18-of-82 1.7 GB: 19-of-82 1.6 GB: 20-of-82 1.7 GB: 21-of-82 1.7 GB: 22-of-82 1.9 GB: 23-of-82 1.9 GB: 24-of-82 1.7 GB: 25-of-82 1.7 GB: 26-of-82 1.7 GB: 27-of-82 1.9 GB: 28-of-82 1.7 GB: 29-of-82 1.7 GB: 30-of-82 1.9 GB: 31-of-82 1.7 GB: 32-of-82 1.7 GB: 33-of-82 1.9 GB: 34-of-82 1.9 GB: 35-of-82 1.6 GB: 36-of-82 1.7 GB: 37-of-82 1.7 GB: 38-of-82 1.9 GB: 39-of-82 1.9 GB: 40-of-82 1.9 GB: 41-of-82 1.9 GB: 42-of-82 1.7 GB: 43-of-82 1.9 GB: 44-of-82 1.9 GB: 45-of-82
Model Architecture	LlamaForCausalLM
License	apache-2.0
Context Length	32768
Model Max Length	32768
Transformers Version	4.39.2
Vocabulary Size	152064
Torch Data Type	bfloat16

Rank the TW3 JRGL V2 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 TW3 JRGL V2

Best Alternatives	Context / RAM	Downloads	Likes
2 Pro Math	128K / 141.9 GB	10	0
Le Triomphant ECE TW3	32K / 79.7 GB	16266	5
Smaug 72B V0.1	32K / 144.5 GB	8736	468
ECE TW3 JRGL V5	32K / 159.6 GB	8245	1
MoMo 72B Lora 1.8.7 DPO	32K / 208.5 GB	314	68
Rhea 72B V0.5	32K / 144.5 GB	8194	134
JuliusCesar 72B BeyonderV.0	32K / 74.2 GB	77	0
Caigun Model 72B KGI	32K / 144.6 GB	31	0
Rhea 125 V0.5	32K / 249 GB	13	1
Exodius 70B	32K / 144.6 GB	8	0