RuvLTRA Small

📱 Compact Model Optimized for Edge Devices

Overview

RuvLTRA Small is a compact 0.5B parameter model designed for edge deployment. Perfect for mobile apps, IoT devices, and resource-constrained environments.

Model Card

Property	Value
Parameters	0.5 Billion
Quantization	Q4_K_M
Context	4,096 tokens
Size	~398 MB
Min RAM	1 GB

🚀 Quick Start

# Download
wget https://huggingface.co/ruv/ruvltra-small/resolve/main/ruvltra-0.5b-q4_k_m.gguf

# Run with llama.cpp
./llama-cli -m ruvltra-0.5b-q4_k_m.gguf -p "Hello, I am" -n 64

💡 Use Cases

Mobile Apps: On-device AI assistant
IoT: Smart home device intelligence
Edge Computing: Local inference without cloud
Prototyping: Quick model experimentation

🔧 Integration

Rust (RuvLLM)

use ruvllm::hub::ModelDownloader;

let path = ModelDownloader::new()
    .download("ruv/ruvltra-small", None)
    .await?;

Python

from huggingface_hub import hf_hub_download

model = hf_hub_download("ruv/ruvltra-small", "ruvltra-0.5b-q4_k_m.gguf")

Hardware Support

✅ Apple Silicon (M1/M2/M3)
✅ NVIDIA CUDA
✅ CPU (x86/ARM)
✅ Raspberry Pi 4/5

License: Apache 2.0 | GitHub: ruvnet/ruvector

⚡ TurboQuant KV-Cache Compression

RuvLTRA models are fully compatible with TurboQuant — 2-4 bit KV-cache quantization that reduces inference memory by 6-8x with <0.5% quality loss.

Quantization	Compression	Quality Loss	Best For
3-bit	10.7x	<1%	Recommended — best balance
4-bit	8x	<0.5%	High quality, long context
2-bit	32x	~2%	Edge devices, max savings

Usage with RuvLLM

cargo add ruvllm    # Rust
npm install @ruvector/ruvllm   # Node.js

use ruvllm::quantize::turbo_quant::{TurboQuantCompressor, TurboQuantConfig, TurboQuantBits};

let config = TurboQuantConfig {
    bits: TurboQuantBits::Bit3_5, // 10.7x compression
    use_qjl: true,
    ..Default::default()
};
let compressor = TurboQuantCompressor::new(config)?;
let compressed = compressor.compress_batch(&kv_vectors)?;
let scores = compressor.inner_product_batch_optimized(&query, &compressed)?;

v2.1.0 Ecosystem

Hybrid Search — Sparse + dense vectors with RRF fusion (20-49% better retrieval)
Graph RAG — Knowledge graph + community detection for multi-hop queries
DiskANN — Billion-scale SSD-backed ANN with <10ms latency
FlashAttention-3 — IO-aware tiled attention, O(N) memory
MLA — Multi-Head Latent Attention (~93% KV-cache compression)
Mamba SSM — Linear-time selective state space models
Speculative Decoding — 2-3x generation speedup

RuVector GitHub | ruvllm crate | @ruvector/ruvllm npm

Benchmarks (L4 GPU, 24GB VRAM)

Metric	Result
Inference Speed	75.4 tok/s
Model Load Time	1.44s
Parameters	0.5B
TurboQuant KV (3-bit)	10.7x compression, <1% PPL loss
TurboQuant KV (4-bit)	8x compression, <0.5% PPL loss

Benchmarked on Google Cloud L4 GPU via ruvltra-calibration Cloud Run Job (2026-03-28)