Trinity-Mini-GGUF

<span style="color: #7FFF7F;">Trinity-Mini GGUF Models</span>

<span style="color: #7F7FFF;">Model Generation Details</span>

This model was generated using llama.cpp at commit 98bd9ab1e.

---

<span style="color: #7FFF7F;">Quantization Beyond the IMatrix</span>

I've been experimenting with a new quantization approach that selectively elevates the precision of key layers beyond what the default IMatrix configuration provides.

In my testing, standard IMatrix quantization underperforms at lower bit depths, especially with Mixture of Experts (MoE) models. To address this, I'm using the --tensor-type option in llama.cpp to manually "bump" important layers to higher precision. You can see the implementation here:
👉 Layer bumping with llama.cpp

While this does increase model file size, it significantly improves precision for a given quantization level.

I'd love your feedback—have you tried this? How does it perform for you?

---

<a href="https://readyforquantum.com/huggingface_gguf_selection_guide.html" style="color: #7FFF7F;"> Click here to get info on choosing the right GGUF model format </a>

---

<!--Begin Original Model Card--> <div align="center"> <picture> <img src="https://cdn-uploads.huggingface.co/production/uploads/6435718aaaef013d1aec3b8b/i-v1KyAMOW_mgVGeic9WJ.png" alt="Arcee Trinity Mini" style="max-width: 100%; height: auto;" > </picture> </div>

Trinity Mini

Trinity Mini is an Arcee AI 26B MoE model with 3B active parameters. It is the medium-sized model in our new Trinity family, a series of open-weight models for enterprise and tinkerers alike.

This model is tuned for reasoning, but in testing, it uses a similar total token count to competitive instruction-tuned models.

---

Trinity Mini is trained on 10T tokens gathered and curated through a key partnership with Datology, building upon the excellent dataset we used on AFM-4.5B with additional math and code.

Training was performed on a cluster of 512 H200 GPUs powered by Prime Intellect using HSDP parallelism.

More details, including key architecture decisions, can be found on our blog here

Try it out now at chat.arcee.ai

---

Model Details

• Model Architecture: AfmoeForCausalLM
• Parameters: 26B, 3B active
• Experts: 128 total, 8 active, 1 shared
• Context length: 128k
• Training Tokens: 10T
• License: Apache 2.0
• Recommended settings:
  • temperature: 0.15
  • top_k: 50
  • top_p: 0.75
  • min_p: 0.06

---

Benchmarks

<div align="center"> <picture> <img src="https://cdn-uploads.huggingface.co/production/uploads/6435718aaaef013d1aec3b8b/sSVjGNHfrJKmQ6w8I18ek.png" style="background-color:ghostwhite;padding:5px;" width="17%" alt="Powered by Datology"> </picture> </div>

Running our model

• Transformers
• VLLM
• llama.cpp
• LM Studio
• API

Transformers

Use the main transformers branch

git clone https://github.com/huggingface/transformers.git
cd transformers

# pip
pip install '.[torch]'

# uv
uv pip install '.[torch]'

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

model_id = "arcee-ai/Trinity-Mini"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto"
)

messages = [
    {"role": "user", "content": "Who are you?"},
]

input_ids = tokenizer.apply_chat_template(
    messages,
    add_generation_prompt=True,
    return_tensors="pt"
).to(model.device)

outputs = model.generate(
    input_ids,
    max_new_tokens=256,
    do_sample=True,
    temperature=0.5,
    top_k=50,
    top_p=0.95
)

response = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(response)

If using a released transformers, simply pass "trust_remote_code=True":

model_id = "arcee-ai/Trinity-Mini"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto",
    trust_remote_code=True
)

VLLM

Supported in VLLM release 0.11.1

# pip
pip install "vllm>=0.11.1"

Serving the model with suggested settings:

vllm serve arcee-train/Trinity-Mini \
  --dtype bfloat16 \
  --enable-auto-tool-choice \
  --reasoning-parser deepseek_r1 \
  --tool-call-parser hermes

llama.cpp

Supported in llama.cpp release b7061

Download the latest llama.cpp release

llama-server -hf arcee-ai/Trinity-Mini-GGUF:q4_k_m \
  --temp 0.15 \
  --top-k 50 \
  --top-p 0.75
  --min-p 0.06

LM Studio

Supported in latest LM Studio runtime

Update to latest available, then verify your runtime by:

1. Click "Power User" at the bottom left
2. Click the green "Developer" icon at the top left
3. Select "LM Runtimes" at the top
4. Refresh the list of runtimes and verify that the latest is installed

Then, go to Model Search and search for arcee-ai/Trinity-Mini-GGUF, download your prefered size, and load it up in the chat

API

Trinity Mini is available today on openrouter:

https://openrouter.ai/arcee-ai/trinity-mini

curl -X POST "https://openrouter.ai/v1/chat/completions" \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "arcee-ai/trinity-mini",
    "messages": [
      {
        "role": "user",
        "content": "What are some fun things to do in New York?"
      }
    ]
  }'

License

Trinity-Mini is released under the Apache-2.0 license.

<!--End Original Model Card-->

---

<span id="testllm" style="color: #7F7FFF;">🚀 If you find these models useful</span>

Help me test my AI-Powered Quantum Network Monitor Assistant with quantum-ready security checks:

👉 Quantum Network Monitor

The full Open Source Code for the Quantum Network Monitor Service available at my github repos ( repos with NetworkMonitor in the name) : Source Code Quantum Network Monitor. You will also find the code I use to quantize the models if you want to do it yourself GGUFModelBuilder

💬 How to test:
Choose an AI assistant type:

• TurboLLM (GPT-4.1-mini)
• HugLLM (Hugginface Open-source models)
• TestLLM (Experimental CPU-only)

What I’m Testing

I’m pushing the limits of small open-source models for AI network monitoring, specifically:

• Function calling against live network services
• How small can a model go while still handling:
  • Automated Nmap security scans
  • Quantum-readiness checks
  • Network Monitoring tasks

🟡 TestLLM – Current experimental model (llama.cpp on 2 CPU threads on huggingface docker space):

• ✅ Zero-configuration setup
• ⏳ 30s load time (slow inference but no API costs) . No token limited as the cost is low.
• 🔧 Help wanted! If you’re into edge-device AI, let’s collaborate!

Other Assistants

🟢 TurboLLM – Uses gpt-4.1-mini :

• **It performs very well but unfortunatly OpenAI charges per token. For this reason tokens usage is limited.
• Create custom cmd processors to run .net code on Quantum Network Monitor Agents
• Real-time network diagnostics and monitoring
• Security Audits
• Penetration testing (Nmap/Metasploit)

🔵 HugLLM – Latest Open-source models:

• 🌐 Runs on Hugging Face Inference API. Performs pretty well using the lastest models hosted on Novita.

💡 Example commands you could test:

1. "Give me info on my websites SSL certificate"
2. "Check if my server is using quantum safe encyption for communication"
3. "Run a comprehensive security audit on my server"
4. '"Create a cmd processor to .. (what ever you want)" Note you need to install a Quantum Network Monitor Agent to run the .net code on. This is a very flexible and powerful feature. Use with caution!

Final Word

I fund the servers used to create these model files, run the Quantum Network Monitor service, and pay for inference from Novita and OpenAI—all out of my own pocket. All the code behind the model creation and the Quantum Network Monitor project is open source. Feel free to use whatever you find helpful.

If you appreciate the work, please consider buying me a coffee ☕. Your support helps cover service costs and allows me to raise token limits for everyone.

I'm also open to job opportunities or sponsorship.

Thank you! 😊