🧠
Trinity Nano Preview Oq4 model by bearzi
⭐ 38.9
🧠
Model

Trinity Nano Preview Oq4

by bearzi hf-model--bearzi--trinity-nano-preview-oq4
Nexus Index
38.9 Top 6%
S: Semantic 50
A: Authority 0
P: Popularity 8
R: Recency 98
Q: Quality 65
Tech Context
1 Params
4.096K Ctx
Vital Performance
96 DL / 30D
0.0%
Source →
Audited 38.9 FNI Score
Tiny 1B Params
4k Context
96 Downloads
8G GPU ~2GB Est. VRAM
MoE Expert AFMOEFORCAUSALLM Architecture
Commercial APACHE License
Model Information Summary
Entity Passport
Registry ID hf-model--bearzi--trinity-nano-preview-oq4
License Apache-2.0
Provider huggingface
💾

Compute Threshold

~2GB VRAM

Interactive
Analyze Hardware
â–ŧ

* Static estimation for 4-Bit Quantization.

📜

Cite this model

Academic & Research Attribution

BibTeX 
@misc{hf_model__bearzi__trinity_nano_preview_oq4,
  author = {bearzi},
  title = {Trinity Nano Preview Oq4 Model},
  year = {2026},
  howpublished = {\url{https://huggingface.co/bearzi/Trinity-Nano-Preview-oQ4}},
  note = {Accessed via Free2AITools Knowledge Fortress}
}
APA Style
bearzi. (2026). Trinity Nano Preview Oq4 [Model]. Free2AITools. https://huggingface.co/bearzi/Trinity-Nano-Preview-oQ4

đŸ”ŦTechnical Deep Dive

Full Specifications [+]

Quick Commands

đŸĻ™ Ollama Run
ollama run trinity-nano-preview-oq4
🤗 HF Download
huggingface-cli download bearzi/trinity-nano-preview-oq4

⚖ī¸ Nexus Index V2.0

Methodology Index Protocol
38.9
TOP 6% SYSTEM IMPACT
Semantic (S) 50
Authority (A) 0
Popularity (P) 8
Recency (R) 98
Quality (Q) 65

đŸ’Ŧ Index Insight

FNI V2.0 for Trinity Nano Preview Oq4: Semantic (S:50), Authority (A:0), Popularity (P:8), Recency (R:98), Quality (Q:65).

Free2AITools Nexus Index

Verification Authority

HuggingFace API GitHub Metadata Arxiv Citation DB System Audit
Unbiased Data Node Refresh: VFS Live
---

🚀 What's Next?

📊

Find Training Datasets

Discover datasets compatible with this model

📈

Compare Benchmarks

See how this model ranks on standard tests

⚡

Deployment Guide

Understand deployment options

Technical Deep Dive

Trinity-Nano-Preview-oQ4

oQ4 mixed-precision MLX quantization produced via oMLX.

  • Quantization: oQ4 (sensitivity-driven mixed precision, group_size=64)
  • Format: MLX safetensors
  • Compatible with: mlx-lm, mlx-vlm, oMLX on Apple Silicon

Usage

python 
from mlx_lm import load, generate
model, tokenizer = load("bearzi/Trinity-Nano-Preview-oQ4")
prompt = tokenizer.apply_chat_template(
    [{"role": "user", "content": "Hello"}],
    add_generation_prompt=True,
)
print(generate(model, tokenizer, prompt=prompt, max_tokens=512, verbose=True))

About oQ

oQ measures per-layer quantization sensitivity through calibration and allocates bits where they matter most — critical layers stay at higher precision, tolerant layers compress aggressively. Target averages of 2/3/4/6/8 bits are provided; actual per-layer bits vary by measured sensitivity.

See oQ documentation.

Comparative benchmarks and feedback welcome — please open a discussion.

⚠ī¸ Incomplete Data

Some information about this model is not available. Use with Caution - Verify details from the original source before relying on this data.

View Original Source →

📝 Limitations & Considerations

  • â€ĸ Benchmark scores may vary based on evaluation methodology and hardware configuration.
  • â€ĸ VRAM requirements are estimates; actual usage depends on quantization and batch size.
  • â€ĸ FNI scores are relative rankings and may change as new models are added.
  • ⚠ License Unknown: Verify licensing terms before commercial use.
Top Tier

Social Proof

HuggingFace Hub
96Downloads
Hub Discussions
🤗 Data Source: Hugging Face ↗
🔄 Daily sync (03:00 UTC)

AI Summary: Based on Hugging Face metadata. Not a recommendation.

📊 FNI Methodology 📚 Knowledge Baseℹī¸ Verify with original source

🛡ī¸ Model Transparency Report

Technical metadata sourced from upstream repositories.

Open Metadata

🆔 Identity & Source

id
hf-model--bearzi--trinity-nano-preview-oq4
slug
bearzi--trinity-nano-preview-oq4
source
huggingface
author
bearzi
license
Apache-2.0
tags
mlx, safetensors, afmoe, omlx, oq, oq4, quantized, text-generation, conversational, custom_code, base_model:arcee-ai/trinity-nano-preview, license:apache-2.0, 4-bit, region:us

⚙ī¸ Technical Specs

architecture
AfmoeForCausalLM
params billions
1
context length
4,096
pipeline tag
text-generation
vram gb
2
vram is estimated
true
vram formula
VRAM ≈ (params * 0.75) + 0.8GB (KV) + 0.5GB (OS)

📊 Engagement & Metrics

downloads
96
stars
0
forks
0

Data indexed from public sources. Updated daily.