Zyphra ZAYA1-8B
MoEApache 2.0
Compact reasoning-tuned MoE trained on AMD GPUs, optimized for intelligence density per parameter. Comfortable fit on a single 12GB card at Q4.
Provider
Zyphra AI
Parameters
8B (MoE)
Context
65.536K
Released
2026-05-04
VRAM Requirements by Quantization
| Method | Disk Size | VRAM Required | Fits GPUs |
|---|---|---|---|
| Q8_0 | 8.5 GB | 9.5 GB | 18 GPUs |
| Q4_K_M | 4.8 GB | 6 GB | 19 GPUs |
| Q4_0 | 4.5 GB | 5.6 GB | 19 GPUs |
Install with Ollama
Benchmark Scores
mmlu73.5%
humaneval68%
Scores are approximate and may vary by quantization level.
Compatible GPUs (19)
AMD RX 9070 XT (16GB)AMD RX 7900 GRE (16GB)AMD RX 7900 XTX (24GB)AMD Ryzen AI Max+ 395 (unified memory) (64GB)Apple M4 Pro (24GB) (24GB)Apple M3 Max (36GB) (36GB)Apple M4 Max (48GB) (48GB)Apple M4 Ultra (64GB) (64GB)NVIDIA RTX 4060 (8GB)NVIDIA RTX 3080 12GB (12GB)NVIDIA RTX 4070 SUPER (12GB)NVIDIA RTX 4070 Ti SUPER (16GB)NVIDIA RTX 4080 SUPER (16GB)NVIDIA RTX 5070 Ti (16GB)NVIDIA RTX 4060 Ti 16GB (16GB)NVIDIA RTX 5080 (16GB)NVIDIA RTX 4090 (24GB)NVIDIA RTX 3090 (24GB)NVIDIA RTX 5090 (32GB)
HuggingFace
Zyphra/ZAYA1-8B