KA

Kanimus 26B A4B FFT Heretic

KanimusGGUF by mradermacherUpdated 2026-10-08
Download on Hugging Face
Parameters25.2B
Context256K
Layers30
Architecturegemma4
Smallest quant10.6 GB
Quick answer

Kanimus 26B A4B FFT Heretic needs about 25.3 GB of memory at Q4_K_M (a 16.8 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 11 quants, from 10.6 GB (Q2_K) to 26.9 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 32.2 GB.

Kanimus 26B A4B FFT Heretic – Gemma4 25.2B parameter model with vision, roleplay, and tools

Kanimus 26B A4B FFT Heretic is a 25.2B parameter Gemma4 model. It supports reasoning, roleplay, tools, and vision. The model is a mixture of experts with 4.0B active parameters and a trained context of 262,144 tokens.

Good at

  • Reasoning
  • Roleplay
  • Vision

Limits

  • Mixture of experts requires large VRAM
  • No language list provided
  • License is gemma

Best for

  • Complex reasoning tasks
  • Interactive roleplay scenarios
  • Vision‑enabled applications

Who it’s for. Developers building advanced conversational agents that need reasoning, roleplay, tools, and vision capabilities. The model is suitable for users with sufficient GPU memory to run the larger quantizations.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K10.6 GB 19.1 GB
Too big Get file →
Q3_K_S12.2 GB 20.8 GB
Too big Get file →
Q3_K_M13.3 GB 21.8 GB
Too big Get file →
Q3_K_L13.8 GB 22.4 GB
Too big Get file →
IQ4_XS14.1 GB 22.6 GB
Too big Get file →
Q4_K_S15.5 GB 24.0 GB
Too big Get file →
Q4_K_M16.8 GB 25.3 GB
Too big Get file →
Q5_K_S18.0 GB 26.5 GB
Too big Get file →
Q5_K_M19.1 GB 27.7 GB
Too big Get file →
Q6_K22.6 GB 31.2 GB
Too big Get file →
Q8_026.9 GB 35.4 GB
Too big Get file →

For 8 GB VRAM, use Q2_K (10.58 GB file, ~19.1 GB memory at 8k context). For 16 GB VRAM, Q4_K_M (16.8 GB file, ~25.3 GB memory). For 32 GB VRAM, Q6_K (22.64 GB file, ~31.2 GB memory).

What GPU do you need for Kanimus 26B A4B FFT Heretic?

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 Q4_K_S (15.5 GB file, about 24.0 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (22.6 GB file, about 31.2 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (26.9 GB file, about 35.4 GB in use).

Which Kanimus 26B A4B FFT Heretic quant should you choose?

Q4_K_M is the usual starting point for Kanimus 26B A4B FFT Heretic: it balances file size and quality well. Here it is a 16.8 GB file.

The Q8_0 file is 26.9 GB, about 1.6 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q2_K at 10.6 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegemma4
Parameters25.2B (approximate, mixture of experts)
Active parameters4B
Layers30
Trained context262,144 tokens
KV cache (fp16)960 KB per token

Source

Quantized bymradermacher
FamilyKanimus
Licensegemma
Downloads (HF)892
Last updated2026-10-08

Frequently asked questions about Kanimus 26B A4B FFT Heretic

How much VRAM does Kanimus 26B A4B FFT Heretic need?

About 25.3 GB at Q4_K_M with an 8K context window. That is the 16.8 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 Kanimus 26B A4B FFT Heretic on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 19.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Kanimus 26B A4B FFT Heretic GGUF?

It depends on the quant: Q2_K is 10.6 GB, Q3_K_S is 12.2 GB, Q3_K_M is 13.3 GB, Q3_K_L is 13.8 GB, IQ4_XS is 14.1 GB, Q4_K_S is 15.5 GB and 5 more.

What context length does Kanimus 26B A4B FFT Heretic 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 Kanimus 26B A4B FFT Heretic GGUF?

The files are on Hugging Face in the mradermacher/Kanimus-26B-A4B-FFT-heretic-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 Kanimus 26B A4B FFT Heretic 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 this model on 8 GB VRAM?

Use the Q2_K quantization; it requires about 19.1 GB memory at 8k context, which is close to 8 GB VRAM but may need off‑load.

Does this model support vision?

Yes, vision is listed as a detected ability.

What is the context length of this model?

The trained context is 262,144 tokens.

Other GGUFs of Kanimus-26B-A4B-FFT-heretic

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Kanimus models

All Kanimus →

Other medium models

All medium models →