BO

Boulesis 26B A4B

BoulesisGGUF by spiritfatherUpdated 2026-09-16
Download on Hugging Face
Parameters26B
Context256K
Layers30
Architecturegemma4
Smallest quant14.3 GB
Quick answer

Boulesis 26B A4B needs about 25.8 GB of memory at Q4_K_M (a 17.2 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 4 quants, from 14.3 GB (IQ4_XS) to 23.2 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 32.2 GB.

Boulesis 26B A4B – a Gemma‑4 based role‑play model

Boulesis 26B A4B is a 26‑billion parameter Gemma‑4 model with a 4‑billion active parameter mixture of experts. It was trained on 262144 context tokens and is optimized for reasoning and tool use in role‑play scenarios.

Good at

  • Reasoning in role‑play
  • Tool integration
  • Deep character context

Limits

  • No vision support
  • Requires large VRAM for full context
  • License is gemma

Best for

  • Complex multi‑character role‑play
  • Narrative writing with deep context
  • Interactive storytelling

Who it’s for. Developers and writers who need a role‑play model that can maintain context over long sessions and integrate tools. It is suitable for projects that require detailed character interactions and reasoning.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ4_XS14.3 GB 22.9 GB
Too big Get file →
Q4_K_M17.2 GB 25.8 GB
Too big Get file →
Q5_K_M19.6 GB 28.2 GB
Too big Get file →
Q6_K23.2 GB 31.8 GB
Too big Get file →

For 8 GB VRAM use IQ4_XS (14.31 GB, 22.9 GB memory at 8 k context). For 12 GB VRAM use Q4_K_M (17.21 GB, 25.8 GB memory). For 16 GB VRAM use Q5_K_M (19.64 GB, 28.2 GB memory).

What GPU do you need for Boulesis 26B A4B?

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: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: the best quant that fits is IQ4_XS (14.3 GB file, about 22.9 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (23.2 GB file, about 31.8 GB in use).

Which Boulesis 26B A4B quant should you choose?

Q4_K_M is the usual starting point for Boulesis 26B A4B: it balances file size and quality well. Here it is a 17.2 GB file.

If memory is tight, the smallest file is IQ4_XS at 14.3 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegemma4
Parameters26B (approximate, mixture of experts)
Active parameters4B
Layers30
Trained context262,144 tokens
KV cache (fp16)960 KB per token

Source

Quantized byspiritfather
FamilyBoulesis
Licensegemma
Downloads (HF)693
Last updated2026-09-16

Frequently asked questions about Boulesis 26B A4B

How much VRAM does Boulesis 26B A4B need?

About 25.8 GB at Q4_K_M with an 8K context window. That is the 17.2 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 Boulesis 26B A4B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 22.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Boulesis 26B A4B GGUF?

It depends on the quant: IQ4_XS is 14.3 GB, Q4_K_M is 17.2 GB, Q5_K_M is 19.6 GB, Q6_K is 23.2 GB.

What context length does Boulesis 26B A4B support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 8.1 GB at 8K and 32.2 GB at 32K.

Where can I download Boulesis 26B A4B GGUF?

The files are on Hugging Face in the spiritfather/Boulesis-26B-A4B-i1-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 Boulesis 26B A4B use?

Hugging Face lists the license as gemma. 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 Boulesis 26B A4B on 8 GB VRAM?

Use the IQ4_XS quant which is 14.31 GB and requires about 22.9 GB memory at 8 k context.

Does this model support vision?

No, Boulesis 26B A4B does not have vision capabilities.

What is the context length of this model?

The model was trained on 262144 context tokens.

Other GGUFs of Boulesis-26B-A4B

Similar models

Browse all →

More from spiritfather

All by spiritfather →

More Boulesis models

All Boulesis →

Other medium models

All medium models →