Grug 3B is an open-source language model by ProCreations. Features: 3b LLM, VRAM: 8.4GB, Context: 256K, License: apache-2.0, LLM Explorer Score: 0.33.
Adaptive-reasoning Base model:finetune:nanbeige/n... Base model:nanbeige/nanbeige4.... Conversational Custom code Dataset:procreations/grug-3b-t... En Grug Nanbeige Reasoning Region:us Safetensors Sharded Tensorflow Token-efficient Tool-use
Model Card on HF 🤗: https://huggingface.co/ProCreations/grug-3b
Grug 3B Benchmarks
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
Grug 3B Parameters and Internals
| LLM Name | Grug 3B |
| Repository 🤗 | https://huggingface.co/ProCreations/grug-3b |
| Base Model(s) | |
| Model Size | 3b |
| Required VRAM | 8.4 GB |
| Updated | 2026-07-27 |
| Maintainer | ProCreations |
| Model Type | nanbeige |
| Model Files | |
| Supported Languages | en |
| Model Architecture | NanbeigeForCausalLM |
| License | apache-2.0 |
| Context Length | 262144 |
| Model Max Length | 262144 |
| Transformers Version | 4.57.6 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <unk> |
| Vocabulary Size | 166144 |
Best Alternatives to Grug 3B
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Nanbeige4.2 3B | 256K / 8.4 GB | 0 | 214 |
| Nanbeige4.2 3B Base | 128K / 8.3 GB | 0 | 29 |
| Nanbeige4.2 3B Mlx 8bit | 256K / 4.4 GB | 269 | 2 |
Note: green Score (e.g. "73.2") means that the model is better than ProCreations/grug-3b .
Rank the Grug 3B Capabilities
🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟
What open-source LLMs or SLMs are you in search of? 55446 in total.
Original data from HuggingFace, Arena and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a