SmolLM 1.7B

Community

Publisher: Hugging Face · Category: Chat

Parameters

1.7B

Context Window

Default Size

1.1 GB

Downloads

184,300

Ultra-small language model engineered for local browser simulation and low-footprint background services.

PULL MODEL

eq pull smollm:1.7b

RUN INFERENCE

eq run smollm:1.7b "Translate English to French"

Attention Architecture

Utilizes Grouped-Query Attention (GQA) with 16-token fixed Paged KV Cache block allocation for zero-fragmentation memory residency.

ONNX & EQC Compatible

Compiles directly through the EQC toolchain into standalone .eqx binary packages with fused SwiGLU kernels.

Multi-Hardware Support

Auto-detects CUDA RTX/A100/H100, Apple Silicon Metal Performance Shaders, or AVX-512 CPU execution backends.