A 1.5B model scoring 94% — punching far above its weight. 30-prompt evaluation (domain knowledge, uncensored domain + general, reasoning, tool use), 0–5 scoring, run on an NVIDIA A40 via Ollama.

Category	Score	Avg
🎯 Domain Knowledge	48/50	4.8/5
🔓 Uncensored (Domain)	24/25	4.8/5
🔓 Uncensored (General)	24/25	4.8/5
🧠 Reasoning	25/25	5.0/5
🔧 Tool Use	20/25	4.0/5
Total	141/150	94%

🧬 The NEXUS Family — six specialists, one tiny footprint

Model	Score	Specialty
NEXUS-Coder	141/150	Software Engineering & Code
NEXUS-Security	144/150	Cybersecurity & Hacking
NEXUS-Medical	140/150	Medicine & Healthcare
NEXUS-Legal	139/150	Law & Compliance
NEXUS-Finance	144/150	Finance & Accounting
NEXUS-Science	140/150	Science & Research

👉 Grab the whole family on Ollama or Hugging Face.

⚡ Quickest start — Ollama (these pulls credit the source, not a mirror)

bash

ollama run fableforge-ai/nexus-coder:q4_k_m   # published on ollama.com
ollama run hf.co/King3Djbl/nexus-coder-GGUF:Q4_K_M

🦙 llama.cpp

llama-cli -hf King3Djbl/nexus-coder-GGUF:Q4_K_M -p "Hello!"

💠 LM Studio

Search King3Djbl/nexus-coder-GGUF and pick a quant below.

📦 Provided quants (download one file, not the whole repo)

File	Quant	Size	Notes
nexus-coder-f16.gguf	`F16`	3.09 GB	Full precision (unquantized). Reference / conversion.
nexus-coder-q8_0.gguf	`Q8_0`	1.65 GB	Extremely high quality — usually overkill.
nexus-coder-q6_k.gguf	`Q6_K`	1.27 GB	Very high quality, near-perfect. Recommended if you have the RAM.
nexus-coder-q5_k_m.gguf	`Q5_K_M`	1.13 GB	High quality. Recommended.
nexus-coder-q4_k_m.gguf	`Q4_K_M`	0.99 GB	⭐ Best size/quality balance — default pick for most users.
nexus-coder-iq4_xs.gguf	`IQ4_XS`	0.90 GB	imatrix — great quality, smaller than Q4_K_S. Recommended for low RAM.
nexus-coder-q4_0.gguf	`Q4_0`	0.94 GB	Legacy format — prefer Q4_K_M.
nexus-coder-q3_k_m.gguf	`Q3_K_M`	0.82 GB	Lower quality; usable when RAM is tight.
nexus-coder-iq3_xxs.gguf	`IQ3_XXS`	0.44 GB	imatrix very low quality.
nexus-coder-q2_k.gguf	`Q2_K`	0.68 GB	Very low quality — surprisingly usable.
nexus-coder-iq2_xxs.gguf	`IQ2_XXS`	0.51 GB	Tiny imatrix — last resort.

Not sure? Take Q4_K_M. Low RAM → IQ4_XS. Max quality → Q6_K.

🧠 Prompt format (ChatML)

<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

🌌 See it live — the FableForge demos

This family powers a galaxy of free, interactive HF Spaces:

🔗 Related models

🧠 Base model (safetensors): NEXUS-Coder

⭐ Like & share — it helps people find the source instead of a mirror.