NanoColibri Instruct is an open-source language model by vovaRL. Features: 2.6b LLM, VRAM: 5.2GB, Context: 4K, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.31.
Arxiv:2304.03208 Base model:finetune:vovarl/nan... Base model:vovarl/nanocolibri-... Conversational Distributed-training Edge-inference En Endpoints compatible From-scratch Hy v3 Instruct Int4 Mixture-of-experts Model-index Moe Region:us Safetensors Small-language-model
Model Card on HF 🤗: https://huggingface.co/vovaRL/NanoColibri-Instruct
NanoColibri Instruct 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)
NanoColibri Instruct Parameters and Internals
| LLM Name | NanoColibri Instruct |
| Repository 🤗 | https://huggingface.co/vovaRL/NanoColibri-Instruct |
| Base Model(s) | |
| Model Size | 2.6b |
| Required VRAM | 5.2 GB |
| Updated | 2026-07-30 |
| Maintainer | vovaRL |
| Model Type | hy_v3 |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | en |
| Model Architecture | HYV3ForCausalLM |
| License | apache-2.0 |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 5.14.1 |
| Tokenizer Class | GPT2Tokenizer |
| Padding Token | <|im_end|> |
| Vocabulary Size | 49152 |
| Errors | replace |
Rank the NanoColibri Instruct 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? 55501 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