---
language:
- en
license: apache-2.0
library_name: gguf
tags:
- ruvltra
- sona
- adaptive-learning
- gguf
- quantized
- turboquant
- kv-cache-compression
- flash-attention
- speculative-decoding
- graph-rag
- hybrid-search
- vector-database
- ruvector
- diskann
- mamba-ssm
- colbert
pipeline_tag: text-generation
---

<div align="center">

# RuvLTRA Medium

[![License](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)
[![HuggingFace](https://img.shields.io/badge/🤗%20Hugging%20Face-Model-yellow)](https://huggingface.co/ruv/ruvltra-medium)
[![GGUF](https://img.shields.io/badge/Format-GGUF-green)](https://github.com/ggerganov/ggml/blob/master/docs/gguf.md)

**⚖️ Balanced Model for General-Purpose Tasks**

</div>

---

## Overview

RuvLTRA Medium provides the sweet spot between capability and resource usage. Ideal for desktop applications, development workstations, and moderate-scale deployments.

## Model Card

| Property | Value |
|----------|-------|
| **Parameters** | 1.1 Billion |
| **Quantization** | Q4_K_M |
| **Context** | 8,192 tokens |
| **Size** | ~669 MB |
| **Min RAM** | 2 GB |
| **Recommended RAM** | 4 GB |

## 🚀 Quick Start

```bash
# Download
wget https://huggingface.co/ruv/ruvltra-medium/resolve/main/ruvltra-1.1b-q4_k_m.gguf

# Run inference
./llama-cli -m ruvltra-1.1b-q4_k_m.gguf \
  -p "Explain quantum computing in simple terms:" \
  -n 512 -c 8192
```

## 💡 Use Cases

- **Development**: Code assistance and generation
- **Writing**: Content creation and editing
- **Analysis**: Document summarization
- **Chat**: Conversational AI applications

## 🔧 Integration

### Rust
```rust
use ruvllm::hub::ModelDownloader;

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

### Python
```python
from llama_cpp import Llama
from huggingface_hub import hf_hub_download

model_path = hf_hub_download("ruv/ruvltra-medium", "ruvltra-1.1b-q4_k_m.gguf")
llm = Llama(model_path=model_path, n_ctx=8192)
```

### OpenAI-Compatible Server

```bash
python -m llama_cpp.server \
  --model ruvltra-1.1b-q4_k_m.gguf \
  --host 0.0.0.0 --port 8000
```

## Performance

| Platform | Tokens/sec |
|----------|------------|
| M2 Pro (Metal) | 65 tok/s |
| RTX 4080 (CUDA) | 95 tok/s |
| i9-13900K (CPU) | 25 tok/s |

---

**License**: Apache 2.0 | **GitHub**: [ruvnet/ruvector](https://github.com/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

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

```rust
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](https://github.com/ruvnet/ruvector) | [ruvllm crate](https://crates.io/crates/ruvllm) | [@ruvector/ruvllm npm](https://www.npmjs.com/package/@ruvector/ruvllm)


---

## Benchmarks (L4 GPU, 24GB VRAM)

| Metric | Result |
|--------|--------|
| **Inference Speed** | 62.6 tok/s |
| **Model Load Time** | 1.1s |
| **Parameters** | 3B |
| **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)*