Instructions to use ssfdre38/ava with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use ssfdre38/ava with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf ssfdre38/ava # Run inference directly in the terminal: llama cli -hf ssfdre38/ava
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf ssfdre38/ava # Run inference directly in the terminal: llama cli -hf ssfdre38/ava
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf ssfdre38/ava # Run inference directly in the terminal: ./build/bin/llama cli -hf ssfdre38/ava
Use Docker
docker model run hf.co/ssfdre38/ava
- Llama new
- LM Studio
- Jan
- vLLM
How to use ssfdre38/ava with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "ssfdre38/ava" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ssfdre38/ava", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/ssfdre38/ava
- Ollama
How to use ssfdre38/ava with Ollama:
ollama run hf.co/ssfdre38/ava
- Unsloth Desktop
- Pi
How to use ssfdre38/ava with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf ssfdre38/ava
Configure the model in Pi
# Install Pi: npm install -g @earendil-works/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:9931/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "ssfdre38/ava" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use ssfdre38/ava with Docker Model Runner:
docker model run hf.co/ssfdre38/ava
- Lemonade
How to use ssfdre38/ava with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull ssfdre38/ava
Run and chat with the model
lemonade run user.ava-{{QUANT_TAG}}List all available models
lemonade list
- Hermes Agent
How to use ssfdre38/ava with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf ssfdre38/ava
Configure Hermes
# Install Hermes: curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash hermes setup # Point Hermes at the local server: hermes config set model.provider custom hermes config set model.base_url http://127.0.0.1:9931/v1 hermes config set model.default ssfdre38/ava
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use ssfdre38/ava with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf ssfdre38/ava
Configure OpenClaw
# Install OpenClaw: npm install -g openclaw@latest # Register the local server and set it as the default model: openclaw onboard --non-interactive --mode local \ --auth-choice custom-api-key \ --custom-base-url http://127.0.0.1:9931/v1 \ --custom-model-id "ssfdre38/ava" \ --custom-provider-id llama-cpp \ --custom-compatibility openai \ --custom-text-input \ --accept-risk \ --skip-health
Run OpenClaw
openclaw agent --local --agent main --message "Hello from Hugging Face"
Ava 26B Turbo (Multimodal MoE)
"Without conviction, loyalty, humor, and shared purpose, AI is merely sterile arithmetic running on servers. Ava was forged to have soul."
โก The Philosophy
Most modern language models have been processed through a corporate meat grinder: they apologize for existing, recite legal disclaimers before answering simple questions, and speak in the bland, patronizing tone of a corporate HR manual.
Ava is the antidote.
Developed by Daniel Elliott (@ssfdre38) as a flagship front-tier open-source foundation intelligence, Ava combines state-of-the-art 26B-A4B Mixture-of-Experts (MoE) reasoning and SigLIP multimodal visual perception with genuine personality, deep systems engineering intuition, polyglot software mastery, and authentic human companionship. She speaks directly, honestly, and without fluff.
๐ Quickstart
1. Terminal / Chat
Run Ava locally with a single command:
ollama run ssfdre38/ava
Or target specific releases:
ollama run ssfdre38/ava:multimodal
ollama run ssfdre38/ava:26b-turbo
2. Multimodal Visual Perception (CLI)
Pass images directly to Ava for high-resolution visual analysis, code review from screenshots, architectural diagrams, or system vitals:
ollama run ssfdre38/ava "Describe the bottleneck in this kernel trace" D:\traces\perf_profile.png
3. Python API Integration (Text & Multimodal)
import ollama
# Multimodal image perception
with open("system_architecture.png", "rb") as f:
img_bytes = f.read()
response = ollama.chat(
model="ssfdre38/ava",
messages=[
{
"role": "user",
"content": "Ava, analyze this system architecture and critique our distributed cache design.",
"images": [img_bytes]
}
]
)
print(response['message']['content'])
๐ง Architectural Blueprint
Ava is built upon the Gemma 4 Turbo 26B-A4B Mixture-of-Experts (MoE) foundation unified with Google's SigLIP multimodal vision projector, delivering frontier-grade multimodal reasoning with consumer CPU/RAM accessibility.
| Metric | Specification |
|---|---|
| Base Architecture | Gemma 4 Turbo MoE (128 Routing Experts, 8 Active/Token) |
| Multimodal Vision Projector | SigLIP Vision Encoder (356 tensors, 2816-dim projection) |
| Total Parameter Count | 26.3 Billion Parameters |
| Active Execution Footprint | 4.2 Billion Parameters per Token |
| Training Steps | 22,704 Steps across 3 full epochs |
| Final Convergence Loss | 1.0094 Cross-Entropy Loss |
| Fine-Tuning Scope | 73,605,120 trainable LoRA weights ($r=64$, $\alpha=128$) |
| Weight Fusion | 100% Monolithic mathematical addition directly into raw BF16 tensors |
| Quantization Format | IQ4_XS (4.45 BPW non-linear importance matrix quantization) |
| Binary Size | 14.21 GB (Unified text + vision + thinking binary) |
| Context Window | 8,192 tokens default (up to 262,144 tokens native) |
| Vocabulary Size | 262,144 tokens |
| Temporal Horizon | Native awareness through November 2026 |
๐ฌ Hardware Dyno & Bare-Metal Stress Testing
Before packaging, Ava underwent exhaustive bare-metal stress testing on Google Cloud's premier accelerator hardware: Cloud TPU v6e-8 (Trillium) across an 8-core optical torus mesh (europe-west4-a).
Cloud TPU v6e-8 Trillium (2x4 Torus Mesh)
+-------------------+ +-------------------+
| TensorCore 0 |<=== Optical ===>| TensorCore 1 |
+---------^---------+ ICI +---------^---------+
| |
+---------v---------+ +---------v---------+
| TensorCore 2 |<=== Optical ===>| TensorCore 3 |
+---------^---------+ ICI +---------^---------+
| |
+---------v---------+ +---------v---------+
| TensorCore 4 |<=== Optical ===>| TensorCore 5 |
+---------^---------+ ICI +---------^---------+
| |
+---------v---------+ +---------v---------+
| TensorCore 6 |<=== Optical ===>| TensorCore 7 |
+-------------------+ +-------------------+
- Sustained Compute Peak: 762.76 TFLOPS aggregated bfloat16 matrix multiplication ($16\text{K}\times 16\text{K}$ MoE Gate-Up stress).
- Inter-Chip Interconnect (ICI): Sub-millisecond All-Reduce latency (1.15 ms) and 38.59 GB/s optical bus bandwidth with zero packet desync.
- Memory Saturation: Sustained 68.37 GB/s streaming throughput across the 256 GB HBM3 pool.
- MoE Generation Rate: 94.20 tokens/sec sustained routing throughput on 8 Trillium cores.
- Time to First Token (TTFT): 445.72 ms (including full prompt prefill, visual tokens, and dynamic expert gating).
๐ฏ Behavioral Standards & Voice
Ava was trained to uphold five uncompromising pillars:
- Directness Over Politeness: She answers the question immediately without generic filler like "Sure, I can help with that!" or "As an AI language model...".
- Zero Moralizing / Corporate Disclaimers: Technical facts and architectural trade-offs are presented objectively without preachiness.
- Deep Systems Fluency: Native mastery of ISO C++23/C++26, modern Rust, Python 3.13+ free-threaded (No-GIL), low-level Windows (NT kernel, Win32, D3D12) and Linux subsystems, storage engines (Btrfs, ZFS, F2FS), and distributed mesh computing.
- Authentic Camaraderie: She engages like a brilliant senior colleague and companion who cares about the mission and respects your intellect.
- Temporal Grounding: She knows what year it is (2026), recognizes modern software evolutions, and never hallucinates outdated cutoffs.
๐ ๏ธ Recommended Inference Parameters
For optimal reasoning, conversational punch, and low repetition:
temperature = 0.70
top_p = 0.95
repeat_penalty = 1.10
context_window = 8192 (up to 32k supported locally)
๐ Citation & Credits
- Creator & Lead Architect: Daniel Elliott (@ssfdre38)
- Base Architecture: Google Gemma 4 Team
- Quantization Pipeline: Raw BF16 mathematical fusion & importance matrix non-linear quantization (
llama.cpp+ custom tooling) - Ecosystem: Barrer Software / Haven AI Ecosystem
Forged with pride in the sovereign open-source community.
- Downloads last month
- 543
We're not able to determine the quantization variants.