Supergemma4 E4B Abliterated needs about 7.2 GB of memory at Q4_K_M (a 5.3 GB file) with an 8K context window, so it fits on a 8 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 5.6 GB.
Supergemma4 E4B Abliterated – a tuned Gemma 4 E4B model for code and tool‑call tasks
Supergemma4 E4B Abliterated is a 7.5 billion‑parameter Gemma 4 model tuned for strong code output, JSON formatting, and tool‑call reliability. It is released as a GGUF file quantized to Q4_K_M and is optimized for low‑friction deployment on Transformers and OpenAI‑compatible stacks.
Good at
- Code generation and bug‑fix
- Structured JSON and tool‑call formatting
- Fast first‑token latency
Limits
- No vision support
- Requires at least 7.2 GB VRAM for 8 k context
- License: gemma
Best for
- Coding assistants
- Bug‑fix assistants
- Agent backends needing strict JSON output
Who it’s for. Developers and teams needing reliable code generation and tool‑call behavior in a lightweight GGUF format. It is suitable for production serving on GPU‑enabled environments with at least 8 GB VRAM.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 5.3 GB | 7.2 GB | Tight | Get file → |
The only available quant is Q4_K_M with a file size of 5.34 GB. It requires approximately 7.2 GB of VRAM when running with an 8 k context. For lower VRAM budgets, no alternative quant is provided.
What GPU do you need for Supergemma4 E4B 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: the best quant that fits is Q4_K_M (5.3 GB file, about 7.2 GB in use).
Which Supergemma4 E4B Abliterated quant should you choose?
Q4_K_M is the usual starting point for Supergemma4 E4B Abliterated: it balances file size and quality well. Here it is a 5.3 GB file.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Supergemma4 E4B Abliterated
How much VRAM does Supergemma4 E4B Abliterated need?
About 7.2 GB at Q4_K_M with an 8K context window. That is the 5.3 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 Supergemma4 E4B Abliterated on an 8 GB GPU?
Yes, with Q4_K_M: the 5.3 GB file needs about 7.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Supergemma4 E4B Abliterated GGUF?
It depends on the quant: Q4_K_M is 5.3 GB.
What context length does Supergemma4 E4B Abliterated support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.4 GB at 8K and 5.6 GB at 32K.
Where can I download Supergemma4 E4B Abliterated GGUF?
The files are on Hugging Face in the NidAll/supergemma4-e4b-abliterated-Q4_K_M-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 Supergemma4 E4B 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?
Yes, the Q4_K_M quant uses about 7.2 GB of VRAM at 8 k context, leaving a small margin for overhead.
Does it support tool calls?
Yes, the model is tuned for tool‑call formatting and has a 90% tool‑call accuracy.
Is it suitable for code generation?
Yes, it achieves 100% exact code score and is designed for coding and bug‑fix assistance.