What are the hardware requirements for Grug 35B V2?

Grug 35B V2 requires approximately 70.3 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Grug 35B V2 and how large is it?

Grug 35B V2 is developed by ProCreations, a model with 35b 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 Grug 35B V2?

Grug 35B V2 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Grug 35B V2 by ProCreations — VRAM 70.3GB

Name: Grug 35B V2
Author: ProCreations

Grug 35B V2 is an open-source language model by ProCreations. Features: 35b LLM, VRAM: 70.3GB, License: apache-2.0, LLM Explorer Score: 0.28.

Agentic Base model:deepreinforce-ai/or... Base model:finetune:deepreinfo... Conversational Dataset:procreations/grug-35b-... Dataset:procreations/grug-35b-... En Grug Moe Qwen3 5 moe Reasoning Region:us Safetensors Sharded Tensorflow Token-efficient Tool-use

Model Card on HF 🤗: https://huggingface.co/ProCreations/grug-35b-v2

Grug 35B V2 Parameters and Internals

LLM Name	Grug 35B V2
Repository 🤗	https://huggingface.co/ProCreations/grug-35b-v2
Base Model(s)	deepreinforce-ai/Ornith-1.0-35B deepreinforce-ai/Ornith-1.0-35B
Model Size	35b
Required VRAM	70.3 GB
Updated	2026-08-12
Maintainer	ProCreations
Model Type	qwen3_5_moe
Model Files	3.8 GB: 1-of-18 3.8 GB: 2-of-18 4.0 GB: 3-of-18 4.0 GB: 4-of-18 3.9 GB: 5-of-18 3.9 GB: 6-of-18 3.9 GB: 7-of-18 4.0 GB: 8-of-18 3.8 GB: 9-of-18 4.0 GB: 10-of-18 4.0 GB: 11-of-18 3.9 GB: 12-of-18 4.0 GB: 13-of-18 3.8 GB: 14-of-18 4.0 GB: 15-of-18 4.0 GB: 16-of-18 3.9 GB: 17-of-18 3.6 GB: 18-of-18
Supported Languages	en
Model Architecture	Qwen3_5MoeForConditionalGeneration
License	apache-2.0
Model Max Length	262144
Transformers Version	5.14.1
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Errors	replace

Rank the Grug 35B 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 Grug 35B V2

Best Alternatives	Context / RAM	Downloads	Likes
....5 35B A3B Sceptic V3 1M W4A16	1024K / 26.1 GB	223	0
...AgentWorld 35B A3B Abliterated	256K / 69.2 GB	962	18
Ornith 1.5 35B A3B NPU2	256K / GB	96	1
Qwen3.6 35B A3B NPU2	256K / GB	107	0
Qwen3.6 35B A3B	0K / 72.2 GB	5540855	2648
Qwen3.5 35B A3B	0K / 72.3 GB	2158511	1482
Qwen3.6 35B A3B NVFP4	0K / 23.4 GB	8788684	482
Ornith 1.0 35B	0K / 70.4 GB	1465715	506
Qwen3.6 35B A3B FP8	0K / 0.8 GB	8984811	343
Qwen AgentWorld 35B A3B	0K / 69.2 GB	66155	665

Note: green Score (e.g. "73.2") means that the model is better than ProCreations/grug-35b-v2.