Zamba2 2.7B Instruct is an open-source language model by Zyphra. Features: 2.7b LLM, VRAM: 5.3GB, Context: 4K, License: apache-2.0, Instruction-Based.
Base model:finetune:zyphra/zam... Base model:zyphra/zamba2-2.7b Conversational Dataset:argilla/openhermespref... Dataset:baai/infinity-instruct Dataset:huggingfaceh4/ultracha... Dataset:huggingfaceh4/ultrafee... Dataset:intel/orca dpo pairs Endpoints compatible Instruct Region:us Safetensors Sharded Tensorflow Zamba2
Model Card on HF 🤗: https://huggingface.co/Zyphra/Zamba2-2.7B-instruct
Zamba2 2.7B Instruct Parameters and Internals
| LLM Name | Zamba2 2.7B Instruct |
| Repository 🤗 | https://huggingface.co/Zyphra/Zamba2-2.7B-instruct |
| Base Model(s) | |
| Model Size | 2.7b |
| Required VRAM | 5.3 GB |
| Updated | 2026-03-30 |
| Maintainer | Zyphra |
| Model Type | zamba2 |
| Instruction-Based | Yes |
| Model Files | |
| Model Architecture | Zamba2ForCausalLM |
| License | apache-2.0 |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 4.49.0.dev0 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | [PAD] |
| Vocabulary Size | 32000 |
Rank the Zamba2 2.7B 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? 52286 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a