Gemma 4 26B A4B Abliterated needs about 21.8 GB of memory at Q3_K_M (a 13.3 GB file) with an 8K context window, so it fits on a 24 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 32.2 GB.
Gemma 4 26B A4B Abliterated – a 25.2B parameter Mixture‑of‑Experts model
Gemma 4 26B A4B Abliterated is a 25.2B parameter model with 4B active parameters in a Mixture‑of‑Experts architecture. It supports reasoning and tool use, and is available in a single Q3_K_M quantized GGUF file.
Good at
- Reasoning
- Tool‑use
- Large context (262144 tokens)
Limits
- Requires ~21.8GB VRAM at 8k context
- Single quant available (Q3_K_M)
- License: gemma
Best for
- Complex reasoning tasks
- Tool‑integrated workflows
- Long‑form text generation
Who it’s for. Developers needing a powerful on‑device LLM with reasoning and tool‑use capabilities. The model is suitable for applications that can accommodate its memory footprint and do not require vision or audio inputs.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_M | 13.3 GB | 21.8 GB | Too big | Get file → |
The only available quant is Q3_K_M, 13.29GB file. It needs about 21.8GB VRAM at 8k context. For lower memory budgets, a different quant would be required, but none are provided.
What GPU do you need for Gemma 4 26B A4B Abliterated?
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 Q3_K_M (13.3 GB file, about 21.8 GB in use).
Which Gemma 4 26B A4B Abliterated quant should you choose?
Q3_K_M (13.3 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Gemma 4 26B A4B Abliterated
How much VRAM does Gemma 4 26B A4B Abliterated need?
About 21.8 GB at Q3_K_M with an 8K context window. That is the 13.3 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 Gemma 4 26B A4B Abliterated on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 21.8 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Gemma 4 26B A4B Abliterated GGUF?
It depends on the quant: Q3_K_M is 13.3 GB.
What context length does Gemma 4 26B A4B Abliterated 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 Gemma 4 26B A4B Abliterated GGUF?
The files are on Hugging Face in the DuoNeural/Gemma-4-26B-A4B-Abliterated-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 Gemma 4 26B A4B Abliterated 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?
No. The Q3_K_M quant requires approximately 21.8GB VRAM at 8k context, exceeding an 8 GB budget.
Does this model support tool use?
Yes. Detected abilities include reasoning and tools.
Is this a Mixture‑of‑Experts model?
Yes. It has 4 active parameters in a MoE architecture.