thoxmini-125m-role needs about 0.9 GB of memory at Q4_K_M (a 0.1 GB file) with an 8K context window, so it fits on a 4 GB GPU.
ThoxMini-125M-role: a fine‑tuned device‑role model
ThoxMini-125M-role is a 0.124 billion‑parameter Llama‑based model fine‑tuned on 1,565 device‑role and chat turns. It is designed for on‑device text generation within the THOX stack. The model is released under Apache‑2.0.
Good at
- Device‑role command handling
- Local text generation
- Edge deployment
Limits
- No vision support
- Not a safety‑aligned public assistant
- Requires THOX guardrails for public use
Best for
- On‑device command execution
- Private local chat
- Edge AI applications
Who it’s for. Developers building on‑device assistants that need a lightweight, device‑role model. Suitable for private or enterprise deployments where local inference is required.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 0.1 GB | 0.6 GB | Fits | Get file → |
The Q4_K_M quantization file is 0.08 GB. It requires approximately 0.9 GB of VRAM at 8 k context. This is the only available quant for this model, so use it for any memory budget above 0.9 GB.
What GPU do you need for thoxmini-125m-role?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: the best quant that fits is Q4_K_M (0.1 GB file, about 0.9 GB in use).
Which thoxmini-125m-role quant should you choose?
Q4_K_M is the usual starting point for thoxmini-125m-role: it balances file size and quality well. Here it is a 0.1 GB file.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about thoxmini-125m-role
How much VRAM does thoxmini-125m-role need?
About 0.9 GB at Q4_K_M with an 8K context window. That is the 0.1 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run thoxmini-125m-role on an 8 GB GPU?
Yes, with Q4_K_M: the 0.1 GB file needs about 0.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of thoxmini-125m-role GGUF?
It depends on the quant: Q4_K_M is 0.1 GB.
What context length does thoxmini-125m-role support?
The GGUF header lists a trained context length of 1,024 tokens (1K). The KV cache grows with the context you use: about 0.3 GB at 8K and 0.0 GB at 1K.
Where can I download thoxmini-125m-role GGUF?
The files are on Hugging Face in the Thox-ai/ThoxMini-125M-role repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does thoxmini-125m-role use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run ThoxMini-125M-role on 8 GB VRAM?
Yes, the Q4_K_M quantization requires about 0.9 GB of VRAM at 8 k context, well within an 8 GB budget.
Is this model safe for public use?
It is not a safety‑aligned public assistant; use it behind THOX guardrails.
What license applies to this model?
Apache‑2.0.