tinybrainbot 100m v4 thinking needs about 0.7 GB of memory at Q8_0 (a 0.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 0.1 GB (Q8_0) to 0.2 GB (F16).
100M-parameter Llama-compatible model focused on reasoning
TinyBrainBot-100M-v4-Thinking is a 100.1M parameter Llama-compatible model with a 1024 token context window. It is trained to produce reasoning traces before answering and is optimized for on-device inference. The model is not aligned or safety-tuned and has limited open‑ended generation.
Good at
- Reasoning with deliberation
- Multiple-choice reasoning
- Chat with on‑device inference
Limits
- Small 1024 token context
- Open‑ended generation limited
- Not aligned or safety‑tuned
Best for
- Reasoning tasks
- Chat with deliberation
- Educational explanations
Who it’s for. Developers building lightweight reasoning assistants, researchers testing small models, and hobbyists who want on‑device reasoning without large GPU resources.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 0.1 GB | 0.6 GB | Fits | Get file → | |
| F16 | 0.2 GB | 0.7 GB | Fits | Get file → |
For 4 GB VRAM, use the Q8_0 GGUF (0.11 GB file, ~0.7 GB memory at 8 k context). For 8 GB VRAM, the F16 GGUF (0.2 GB file, ~0.8 GB memory) is suitable. Memory estimates are approximate.
What GPU do you need for tinybrainbot 100m v4 thinking?
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 F16 (0.2 GB file, about 0.8 GB in use).
Which tinybrainbot 100m v4 thinking quant should you choose?
Q8_0 (0.1 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about tinybrainbot 100m v4 thinking
How much VRAM does tinybrainbot 100m v4 thinking need?
About 0.7 GB at Q8_0 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 tinybrainbot 100m v4 thinking on an 8 GB GPU?
Yes, with F16: the 0.2 GB file needs about 0.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of tinybrainbot 100m v4 thinking GGUF?
It depends on the quant: Q8_0 is 0.1 GB, F16 is 0.2 GB.
What context length does tinybrainbot 100m v4 thinking support?
The GGUF header lists a trained context length of 1,024 tokens (1K). The KV cache grows with the context you use: about 0.1 GB at 8K and 0.0 GB at 1K.
Where can I download tinybrainbot 100m v4 thinking GGUF?
The files are on Hugging Face in the nkthebass/tinybrainbot-100m-v4-thinking repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does tinybrainbot 100m v4 thinking 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 TinyBrainBot-100M-v4-Thinking on 4 GB VRAM?
Yes, the Q8_0 GGUF requires about 0.7 GB of VRAM at 8 k context, which fits within 4 GB.
Is this model compatible with llama.cpp?
Yes, the GGUF files are designed for llama.cpp, Ollama, and LM Studio.
Does TinyBrainBot-100M-v4-Thinking support vision?
No, the model has no vision capabilities.