TI

TinyBrainBot-360M-A75M-v4.1-MoE-Base

TinybrainbotGGUF by nkthebassUpdated 2026-10-19
Download on Hugging Face
Parameters383M
Context2K
Layers12
Architecturellama
Smallest quant0.4 GB
Quick answer

TinyBrainBot-360M-A75M-v4.1-MoE-Base needs about 1.0 GB of memory at Q8_0 (a 0.4 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 0.4 GB (Q8_0) to 0.8 GB (F16).

Mixture-of-experts Llama model with 360M parameters

TinyBrainBot-360M-A75M-v4.1-MoE-Base is a mixture-of-experts language model based on Llama architecture. It contains 24 experts per layer and uses 4 experts per token, resulting in 75.7M active parameters per token. The model was trained on 18.2B tokens with a 2,048-token context.

Good at

  • Efficient token‑level inference
  • Low per‑token compute
  • Factual question answering patch

Limits

  • Requires 2,048-token context
  • No vision support
  • Apache‑2.0 license

Best for

  • Chatbots needing quick responses
  • Lightweight inference on GPUs
  • Fine‑tuning with expert patches

Who it’s for. Developers building lightweight LLM applications who need a mixture‑of‑experts model with lower per‑token compute. The model is suitable for projects that can work within a 2,048‑token context and require an Apache‑2.0 licensed model.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_00.4 GB 0.9 GB
Fits Get file →
F160.8 GB 1.3 GB
Fits Get file →

For 8 GB VRAM, use the Q8_0 quantized file (0.41 GB, ~1 GB memory at 8k context). If more VRAM is available, the F16 quantized file (0.77 GB, ~1.4 GB memory at 8k context) offers higher precision. Memory estimates are approximate.

What GPU do you need for TinyBrainBot-360M-A75M-v4.1-MoE-Base?

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 (0.8 GB file, about 1.4 GB in use).

Which TinyBrainBot-360M-A75M-v4.1-MoE-Base quant should you choose?

Q8_0 (0.4 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

Architecturellama
Parameters383M (approximate, mixture of experts)
Layers12
Trained context2,048 tokens
KV cache (fp16)12 KB per token

Source

Quantized bynkthebass
Licenseapache-2.0
Downloads (HF)660
Last updated2026-10-19

Frequently asked questions about TinyBrainBot-360M-A75M-v4.1-MoE-Base

How much VRAM does TinyBrainBot-360M-A75M-v4.1-MoE-Base need?

About 1.0 GB at Q8_0 with an 8K context window. That is the 0.4 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-360M-A75M-v4.1-MoE-Base on an 8 GB GPU?

Yes, with F16: the 0.8 GB file needs about 1.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of TinyBrainBot-360M-A75M-v4.1-MoE-Base GGUF?

It depends on the quant: Q8_0 is 0.4 GB, F16 is 0.8 GB.

What context length does TinyBrainBot-360M-A75M-v4.1-MoE-Base support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 0.1 GB at 8K and 0.0 GB at 2K.

Where can I download TinyBrainBot-360M-A75M-v4.1-MoE-Base GGUF?

The files are on Hugging Face in the nkthebass/tinybrainbot-360m-a75m-v4.1-moe-base 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-360M-A75M-v4.1-MoE-Base 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-360M-A75M-v4.1-MoE-Base on 8 GB VRAM?

Yes, the Q8_0 quantized file is 0.41 GB and requires about 1 GB of VRAM at 8k context, which fits within 8 GB.

Does this model support vision tasks?

No, the model is purely a language model and does not support vision.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Similar models

Browse all →

More from nkthebass

All by nkthebass →

More Tinybrainbot models

All Tinybrainbot →

Other tiny models

All tiny models →