BA

Basal Omni 1.0 Mini

BasalGGUF by RemekUpdated 2026-10-28
Download on Hugging Face
Parameters7.46B
Context128K
Layers42
Architecturegemma4
Smallest quant6.2 GB
Quick answer

Basal Omni 1.0 Mini needs about 8.1 GB of memory at Q6_K (a 6.2 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 4 quants, from 6.2 GB (Q6_K) to 7.9 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 5.6 GB.

Basal Omni 1.0 Mini – a 7.46B Gemma 4 E4B decision model

Basal Omni 1.0 Mini is a 7.46B parameter Gemma 4 E4B model trained for typed decision tasks. It supports reasoning and tool usage and can handle up to 131072 context tokens. The model is released under the apache-2.0 license.

Good at

  • Reasoning on typed decisions
  • Tool selection
  • Zero‑shot image and audio queries (via separate encoders)

Limits

  • No vision or audio in GGUF files
  • Requires 8.1–9.9 GB VRAM for Q6_K/Q8_0
  • Large context but no image/audio encoders

Best for

  • Decision‑making assistants
  • Tool‑enabled agents
  • Rapid prototyping of decision APIs

Who it’s for. Developers building decision‑oriented agents who need a lightweight Gemma 4 base. The model is suitable for CPU, Apple Silicon, or NVIDIA GPU deployments via llama.cpp or Ollama.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q6_K6.2 GB 8.1 GB
Too big Get file →
Q6_K6.2 GB 8.1 GB
Too big Get file →
Q8_07.9 GB 9.9 GB
Too big Get file →
Q8_07.9 GB 9.9 GB
Too big Get file →

For 8 GB VRAM use the Q6_K quant (file size 6.17 GB, estimated 8.1 GB VRAM). For 10 GB VRAM use Q8_0 (file size 7.95 GB, estimated 9.9 GB VRAM). Both quants provide similar accuracy to bf16.

What GPU do you need for Basal Omni 1.0 Mini?

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: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: the best quant that fits is Q8_0 (7.9 GB file, about 9.9 GB in use).

Which Basal Omni 1.0 Mini quant should you choose?

Q6_K (6.2 GB) is the middle option in this repository. Very close to the original quality for most uses, at a clearly larger size than 4-bit.

If memory is tight, the smallest file is Q6_K at 6.2 GB, with the quality trade-offs that come with fewer bits. Very close to the original quality for most uses, at a clearly larger size than 4-bit.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegemma4
Parameters7.46B
Layers42
Trained context131,072 tokens
KV cache (fp16)168 KB per token

Source

Quantized byRemek
FamilyBasal
Licenseapache-2.0
Downloads (HF)767
Last updated2026-10-28

Frequently asked questions about Basal Omni 1.0 Mini

How much VRAM does Basal Omni 1.0 Mini need?

About 8.1 GB at Q6_K with an 8K context window. That is the 6.2 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 Basal Omni 1.0 Mini on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 8.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Basal Omni 1.0 Mini GGUF?

It depends on the quant: Q6_K is 6.2 GB, Q6_K is 6.2 GB, Q8_0 is 7.9 GB, Q8_0 is 7.9 GB.

What context length does Basal Omni 1.0 Mini support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.4 GB at 8K and 5.6 GB at 32K.

Where can I download Basal Omni 1.0 Mini GGUF?

The files are on Hugging Face in the Remek/basal-omni-1.0-mini-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Basal Omni 1.0 Mini 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 Basal Omni 1.0 Mini on 8 GB VRAM?

Yes, the Q6_K quant requires approximately 8.1 GB VRAM, which fits on an 8 GB GPU with some headroom.

Does the GGUF version support image or audio input?

No. The GGUF files contain only text weights; image and audio encoders are not included.

What license applies to this model?

The model is released under the apache-2.0 license.

Similar models

Browse all →

More from Remek

All by Remek →

More Basal models

All Basal →

Other small models

All small models →