LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  Agents   Benchmarks   LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Zamba 7B V1 by Zyphra

 »  All LLMs  »  Zyphra  »  Zamba 7B V1   URL Share it on

  3914   

Zamba 7B V1 is an open-source language model by Zyphra. Features: 7b LLM, VRAM: 14.5GB, Context: 4K, License: apache-2.0, LLM Explorer Score: 0.16.

  Arxiv:2405.16712   Endpoints compatible   Region:us   Safetensors   Sharded   Tensorflow   Zamba
Model Card on HF 🤗: https://huggingface.co/Zyphra/Zamba-7B-v1 

Zamba 7B V1 Benchmarks

LLME Score: 0.15998
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Zamba 7B V1 (Zyphra/Zamba-7B-v1)
🌟 Advertise your project 🚀

Zamba 7B V1 Parameters and Internals

Model Type 
Hybrid State-Space Model, Transformer
Additional Notes 
Zamba is a pretrained base model and does not have moderation mechanisms. It is not fine-tuned for chat and expect reduced performance in chat applications.
Supported Languages 
languages_supported ()
Training Details 
Data Sources:
Open web datasets, 1T tokens for initial pretraining, 50B high-quality tokens for second phase
Data Volume:
1T tokens for initial pretraining
Methodology:
Next-token prediction
Model Architecture:
Hybrid SSM with a backbone of Mamba layers and shared transformer layers interspersed every 6 blocks
Input Output 
Input Format:
Text input
Accepted Modalities:
Text
Output Format:
Text output
Performance Tips:
Running optimized Mamba implementations on a CUDA device is recommended for best performance.
LLM NameZamba 7B V1
Repository 🤗https://huggingface.co/Zyphra/Zamba-7B-v1 
Model Size7b
Required VRAM14.5 GB
Updated2026-04-04
MaintainerZyphra
Model Typezamba
Model Files  4.9 GB: 1-of-3   5.0 GB: 2-of-3   4.6 GB: 3-of-3   14.7 GB
Model ArchitectureZambaForCausalLM
Licenseapache-2.0
Context Length4096
Model Max Length4096
Transformers Version4.45.0.dev0
Tokenizer ClassLlamaTokenizer
Padding Token[PAD]
Vocabulary Size32000
Torch Data Typebfloat16

Best Alternatives to Zamba 7B V1

Best Alternatives
Context / RAM
Downloads
Likes
Zamba 7B V1 Phase14K / 14.5 GB95

Rank the Zamba 7B V1 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! 🌟

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  

What open-source LLMs or SLMs are you in search of? 52721 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer