llama-gguf
v0.14.0 ExperimentalA high-performance Rust implementation of llama.cpp - LLM inference engine with full GGUF support
Quick Verdict
- !Pre-1.0: API may have breaking changes
- โTrusted by 122 crates
- !Heavy dependency tree (43 direct deps)
- โPermissive license (MIT OR Apache-2.0)
Security
Deep Insights
2.0K downloads in the last 30 days (66/day), up 353% from the previous period.
122 crates depend on llama-gguf. Reasonable ecosystem adoption, though not yet a core dependency.
The primary maintainer publishes 200 crates. This suggests deep Rust expertise and long-term commitment to the ecosystem.
43 direct dependencies. Consider the impact on compile times and supply chain complexity.
Notable dependents include oxios-kernel, oxios-memory, sqlite-vector-rs, rust-agent-llama. When high-quality crates choose llama-gguf, it's a strong quality signal.
Health Breakdown
Recency, release consistency, active ratio
Yanked ratio, deps, size, maturity, features
Reverse deps, ownership, ecosystem
Downloads, momentum, growth trend
Docs, repo, license, metadata
Download Trend
Top Dependents
Most downloaded crates that depend on llama-gguf
Version Adoption
Release Timeline
Feature Flags
default =["cpu", "huggingface", "cli", "client", "onnx", "server"]