BO

Boulesis v2 26B A4B

BoulesisGGUF by mradermacherUpdated 2026-09-17
Download on Hugging Face
Parameters26B
Context256K
Layers30
Architecturegemma4
Smallest quant0.1 GB
Quick answer

Boulesis v2 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 24 quants, from 0.1 GB to 23.2 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 32.2 GB.

Boulesis v2 26B A4B – a Gemma4 Mixture of Experts model

Boulesis v2 26B A4B is a 26‑billion‑parameter Gemma4 architecture with 4 billion active parameters. It is a Mixture of Experts model trained on 262 144 context tokens. The model focuses on reasoning and roleplay abilities.

Good at

  • Reasoning
  • Roleplay
  • Context‑deep character memory

Limits

  • No vision support
  • Requires large VRAM for higher‑quality quants
  • License is gemma

Best for

  • Complex role‑play sessions
  • Long‑form reasoning tasks
  • Character‑driven storytelling

Who it’s for. Developers and researchers who need a large Gemma4 model with strong reasoning and role‑play capabilities. Suitable for applications that can allocate sufficient VRAM and RAM for the chosen quant.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.1 GB 8.6 GB
Too big Get file →
IQ1_S8.5 GB 17.1 GB
Too big Get file →
IQ1_M8.9 GB 17.5 GB
Too big Get file →
IQ2_XXS9.5 GB 18.1 GB
Too big Get file →
IQ2_XS10.1 GB 18.6 GB
Too big Get file →
IQ2_S10.2 GB 18.7 GB
Too big Get file →
IQ2_M10.7 GB 19.2 GB
Too big Get file →
Q2_K10.8 GB 19.4 GB
Too big Get file →
Q2_K_S10.9 GB 19.4 GB
Too big Get file →
IQ3_XXS11.6 GB 20.2 GB
Too big Get file →
IQ3_XS12.0 GB 20.5 GB
Too big Get file →
IQ3_S12.5 GB 21.1 GB
Too big Get file →
Q3_K_S12.5 GB 21.1 GB
Too big Get file →
IQ3_M12.7 GB 21.3 GB
Too big Get file →
Q3_K_M13.6 GB 22.2 GB
Too big Get file →
Q3_K_L14.1 GB 22.7 GB
Too big Get file →
IQ4_XS14.3 GB 22.9 GB
Too big Get file →
Q4_014.9 GB 23.5 GB
Too big Get file →
Q4_K_S15.9 GB 24.4 GB
Too big Get file →
Q4_116.4 GB 25.0 GB
Too big Get file →
Q4_K_M17.2 GB 25.8 GB
Too big Get file →
Q5_K_S18.5 GB 27.0 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 IQ1_S (8.53 GB, 17.1 GB memory) or IQ1_M (8.91 GB, 17.5 GB memory). For 12 GB VRAM, IQ2_S (10.06 GB, 18.6 GB memory) or Q2_K (10.82 GB, 19.4 GB memory) are suitable. Higher‑quality IQ4 or Q5 quants require 16 GB or more VRAM.

What GPU do you need for Boulesis v2 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: the best quant that fits is the main file (0.1 GB file, about 8.6 GB in use).
  • 16 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 8.6 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_0 (14.9 GB file, about 23.5 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 v2 26B A4B quant should you choose?

Q4_K_M is the usual starting point for Boulesis v2 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 the first one in the table at 0.1 GB, with the quality trade-offs that come with fewer bits.

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 bymradermacher
FamilyBoulesis
Licensegemma
Downloads (HF)1,930
Last updated2026-09-17

Frequently asked questions about Boulesis v2 26B A4B

How much VRAM does Boulesis v2 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 v2 26B A4B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 8.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Boulesis v2 26B A4B GGUF?

It depends on the quant: file is 0.1 GB, IQ1_S is 8.5 GB, IQ1_M is 8.9 GB, IQ2_XXS is 9.5 GB, IQ2_XS is 10.1 GB, IQ2_S is 10.2 GB and 18 more.

What context length does Boulesis v2 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 v2 26B A4B GGUF?

The files are on Hugging Face in the mradermacher/Boulesis-v2-26B-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 v2 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 v2 26B A4B on 8 GB VRAM?

Use the IQ1_S or IQ1_M quant. They are the smallest quants that fit 8 GB VRAM and provide acceptable performance.

Does this model support vision tasks?

No. The model is a text‑only model; vision support is not included.

What sampler settings are recommended?

Temperature 1.0, Top‑K 64, Repetition Penalty 1.05‑1.1, Top‑P 0.95 are recommended for best results.

Other GGUFs of Boulesis-v2-26B-A4B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Boulesis models

All Boulesis →

Other medium models

All medium models →