Thox-ai/thox-micro-125m-GGUF overview
thox micro 125m GGUF License https://img.shields.io/badge/License apache 2.0 05A451 Params https://img.shields.io/badge/Params 123M 05A451 Base https://img.shi…
Runs locally from ~77.6 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
Model Details
| Model ID | Thox-ai/thox-micro-125m-GGUF |
|---|---|
| Author | Thox-ai |
| Pipeline | text-generation |
| License | apache-2.0 |
| Base model | Thox-ai/thox-micro-125m |
| Last modified | 2026-08-11T11:03:35.000Z |
Model README
---
license: apache-2.0
pipeline_tag: text-generation
library_name: gguf
base_model:
- Thox-ai/thox-micro-125m
language:
- en
tags:
- thox
- gguf
- llama.cpp
- q4_0
- armv6
- from-scratch
- on-device
- edge
---
thox-micro-125m-GGUF
!License !Params !Base !GGUF !Format
> Your AI. Your Data. Your Rules.
GGUF builds (Q4_0 → F16) of the from-scratch thox-micro-125m for llama.cpp / on-device.
What this is
- Quantized from Thox-ai/thox-micro-125m (Apache-2.0).
- Q4_0 is usable because FFN 2048 is divisible by 32 (unlike the 327M).
- SHA256SUMS.txt included for verification.
Intended use
On-device / edge text generation within the THOX stack. Not a safety-aligned public assistant unless deployed behind THOX guardrails.
Usage
llama.cpp
huggingface-cli download Thox-ai/thox-micro-125m-GGUF --include '*.gguf' --local-dir ./thox-micro-125m-GGUF
llama-cli -m ./thox-micro-125m-GGUF/model-Q4_0.gguf -p "Hello"Links
- Base model:
Thox-ai/thox-micro-125m - Weights source (HF):
Thox-ai/thox-micro-125m - Ollama:
ollama.com/thox-ai/<slug>— _verify with the Ollama lane (task 80017303)_ - Docs: https://docs.thox.ai
---
THOX.ai LLC — Your AI. Your Data. Your Rules. · On-device and private by design.
Run Thox-ai/thox-micro-125m-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models