Model Intelligence Sheet
breitburg/pure-reasoning-7b-230726-GGUF overview
pure reasoning 7b 230726 GGUF GGUF build of breitburg/pure reasoning 7b 230726 https://huggingface.co/breitburg/pure reasoning 7b 230726 , a thinking model tha…
Runs locally from ~3.80 GB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
Model Details
Model README
---
tags:
- gguf
- llama.cpp
- unsloth
- reasoning
---
pure-reasoning-7b-230726-GGUF
GGUF build of breitburg/pure-reasoning-7b-230726,
a thinking model that emits a <think>...</think> block then an answer. Converted 23 July 2026
with Unsloth. The ChatML chat template is embedded in the
GGUF, so pass --jinja.
Example usage:
llama-cli -hf breitburg/pure-reasoning-7b-230726-GGUF:Q8_0 --jinja
Available files
pure-reasoning-7b-230726.Q8_0.gguf— ~7.2 GB, higher qualitypure-reasoning-7b-230726.Q4_K_M.gguf— ~4 GB, smaller/faster
Trained 2x faster with Unsloth.
Run breitburg/pure-reasoning-7b-230726-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models