TinyLlama-1.1B-Chat-v1.0-zse-int4

Pre-converted ZSE model for ultra-fast inference.

Source Model

• Original: TinyLlama/TinyLlama-1.1B-Chat-v1.0
• Quantization: INT4
• File Size: 0.71 GB
• Format: ZSE binary (.zse)

Usage

pip install zllm-zse

# Download and serve
zse pull tinyllama-1.1b-chat-v1.0
zse serve tinyllama-1.1b-chat-v1.0

# Or direct
zse serve TinyLlama-1.1B-Chat-v1.0-zse-int4.zse

Benefits

• 5x faster cold start compared to HuggingFace loading
• 10-14% less VRAM with ZSE custom INT4 kernels
• Single file — tokenizer and config embedded
• No internet required after download

Benchmarks

See ZSE Documentation for full benchmarks.

---

Converted with ZSE v1.4.0