Zaya1 Base 8B 8bit MLX is an open-source language model by kyr0. Features: 8b LLM, VRAM: 9.5GB, Context: 128K, License: apache-2.0, Quantized, LLM Explorer Score: 0.33.
Arxiv:2510.04476 Arxiv:2511.17127 8-bit 8bit Base model:quantized:zyphra/za... Base model:zyphra/zaya1-8b Conversational Mlx Quantized Region:us Safetensors Sharded Tensorflow Zaya
Model Card on HF 🤗: https://huggingface.co/kyr0/zaya1-base-8b-8bit-MLX
Zaya1 Base 8B 8bit MLX 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)
Zaya1 Base 8B 8bit MLX Parameters and Internals
| LLM Name | Zaya1 Base 8B 8bit MLX |
| Repository 🤗 | https://huggingface.co/kyr0/zaya1-base-8b-8bit-MLX |
| Base Model(s) | |
| Model Size | 8b |
| Required VRAM | 9.5 GB |
| Updated | 2026-05-10 |
| Maintainer | kyr0 |
| Model Type | zaya |
| Model Files | |
| Quantization Type | 8bit |
| Model Architecture | ZayaForCausalLM |
| License | apache-2.0 |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.57.1 |
| Tokenizer Class | GemmaTokenizer |
| Padding Token | <pad> |
| Vocabulary Size | 262272 |
Best Alternatives to Zaya1 Base 8B 8bit MLX
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ZAYA1 8B | 128K / 17.7 GB | 44834 | 365 |
Note: green Score (e.g. "73.2") means that the model is better than kyr0/zaya1-base-8b-8bit-MLX .
Rank the Zaya1 Base 8B 8bit MLX 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? 53620 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