GE

ThinkingCap Gemma 4 26B A4B It

GemmaGGUF by bartowskiUpdated 2026-10-23
Download on Hugging Face
Parameters25.2B
Context256K
Layers30
Architecturegemma4
Smallest quant0.1 GB
Quick answer

ThinkingCap Gemma 4 26B A4B It needs about 26.5 GB of memory at Q4_K_M (a 18.0 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 50.5 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 32.2 GB.

ThinkingCap Gemma 4 26B A4B It – a multimodal, mixture‑of‑experts LLM with reasoning and tool use

ThinkingCap Gemma 4 26B A4B It is a 26B‑parameter mixture‑of‑experts model based on gemma4. It supports text, image and audio input and includes a reasoning engine that can be enabled with `enable_thinking=True`. The model is licensed under apache‑2.0.

Good at

  • Reasoning with low token cost
  • Tool use and agentic tasks
  • Multimodal input (image, audio)

Limits

  • Requires 8‑k context for memory estimates
  • No speculative decoding
  • No built‑in vision projector in the base GGUF

Best for

  • Chatbots needing efficient reasoning
  • Agents that call external tools
  • Multimodal content generation

Who it’s for. Developers building chat or agent applications that need reasoning and multimodal input. The model is suitable for users who can enable the reasoning feature and have access to a compatible llama.cpp release.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.1 GB 8.7 GB
Too big Get file →
IQ2_XS9.9 GB 18.4 GB
Too big Get file →
IQ2_S10.3 GB 18.9 GB
Too big Get file →
IQ2_M10.9 GB 19.5 GB
Too big Get file →
Q2_K11.6 GB 20.2 GB
Too big Get file →
Q3_K_S12.4 GB 20.9 GB
Too big Get file →
IQ3_XXS12.6 GB 21.2 GB
Too big Get file →
IQ3_XS12.8 GB 21.4 GB
Too big Get file →
Q3_K_M13.8 GB 22.3 GB
Too big Get file →
IQ4_XS14.3 GB 22.8 GB
Too big Get file →
Q4_014.8 GB 23.3 GB
Too big Get file →
Q3_K_L14.8 GB 23.4 GB
Too big Get file →
IQ4_NL15.6 GB 24.2 GB
Too big Get file →
Q4_K_S16.1 GB 24.6 GB
Too big Get file →
Q4_116.1 GB 24.7 GB
Too big Get file →
Q4_K_M18.0 GB 26.5 GB
Too big Get file →
Q4_K_L18.2 GB 26.8 GB
Too big Get file →
Q5_K_S18.4 GB 27.0 GB
Too big Get file →
Q5_K_M20.0 GB 28.6 GB
Too big Get file →
Q6_K_S23.1 GB 31.7 GB
Too big Get file →
Q6_K23.8 GB 32.3 GB
Too big Get file →
Q6_K_L24.5 GB 33.1 GB
Too big Get file →
Q8_026.9 GB 35.4 GB
Too big Get file →
BF1650.5 GB 59.1 GB
Too big Get file →

For 8‑GB VRAM, use IQ2_XS (9.9 GB) or Q2_K (11.61 GB). For 16‑GB VRAM, Q4_K_M (17.97 GB) offers a good balance of size and performance. For 32‑GB VRAM, Q6_K (23.79 GB) or Q8_0 (26.86 GB) provide higher fidelity.

What GPU do you need for ThinkingCap Gemma 4 26B A4B It?

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 8.7 GB in use).
  • 16 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 8.7 GB in use).
  • 24 GB VRAM: the best quant that fits is Q3_K_L (14.8 GB file, about 23.4 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K_S (23.1 GB file, about 31.7 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 ThinkingCap Gemma 4 26B A4B It quant should you choose?

Q4_K_M is the usual starting point for ThinkingCap Gemma 4 26B A4B It: it balances file size and quality well. Here it is a 18.0 GB file.

The Q8_0 file is 26.9 GB, about 1.5 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 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
Parameters25.2B (approximate, mixture of experts)
Active parameters4B
Layers30
Trained context262,144 tokens
KV cache (fp16)960 KB per token

Source

Quantized bybartowski
FamilyGemma
Licenseapache-2.0
Downloads (HF)3,669
Last updated2026-10-23

Frequently asked questions about ThinkingCap Gemma 4 26B A4B It

How much VRAM does ThinkingCap Gemma 4 26B A4B It need?

About 26.5 GB at Q4_K_M with an 8K context window. That is the 18.0 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 ThinkingCap Gemma 4 26B A4B It on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 8.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of ThinkingCap Gemma 4 26B A4B It GGUF?

It depends on the quant: file is 0.1 GB, IQ2_XS is 9.9 GB, IQ2_S is 10.3 GB, IQ2_M is 10.9 GB, Q2_K is 11.6 GB, Q3_K_S is 12.4 GB and 18 more.

What context length does ThinkingCap Gemma 4 26B A4B It 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 ThinkingCap Gemma 4 26B A4B It GGUF?

The files are on Hugging Face in the bartowski/bottlecapai_ThinkingCap-gemma-4-26B-A4B-it-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 ThinkingCap Gemma 4 26B A4B It 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 this model on 8 GB VRAM?

Yes, the IQ2_XS quant is 9.9 GB and the Q2_K quant is 11.61 GB, both within 8‑GB VRAM limits with some swap.

Does the model support vision?

The base GGUF does not include a vision projector; image input requires a separate mmproj file.

What is the context length?

The model was trained with 262144 tokens and can operate with that context length in llama.cpp.

Other GGUFs of ThinkingCap-gemma-4-26B-A4B-it

Similar models

Browse all →

More from bartowski

All by bartowski →

More Gemma models

All Gemma →

Other medium models

All medium models →