SuperGemma 4 12b Abliterated needs about 20.8 GB of memory at Q4_K_M (a 7.4 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 11 quants, from 4.8 GB (Q2_K) to 12.7 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 51.5 GB.
SuperGemma 4 12b Abliterated – a 12B Gemma4 model optimized for direct task completion
SuperGemma 4 12b Abliterated is a fused 12B checkpoint derived from google/gemma-4-12B-it. It combines an ablation pass to reduce unnecessary refusals with a supertune post‑training for instruction following, coding, Korean technical answers, JSON/tool formatting, and regression resistance.
Good at
- Coding
- Reasoning
- Vision
Limits
- No runtime adapters required
- Requires 8k context for full performance
- Apache‑2.0 license
Best for
- Instruction following
- Tool‑based code generation
- JSON formatting
Who it’s for. Developers and researchers needing a 12B Gemma4 model with reduced refusal behavior and strong coding and reasoning abilities. The model is suitable for local deployment via llama.cpp.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 4.8 GB | 18.2 GB | Too big | Get file → | |
| Q3_K_S | 5.5 GB | 18.9 GB | Too big | Get file → | |
| Q3_K_M | 6.1 GB | 19.5 GB | Too big | Get file → | |
| Q3_K_L | 6.6 GB | 20.0 GB | Too big | Get file → | |
| IQ4_XS | 6.7 GB | 20.1 GB | Too big | Get file → | |
| Q4_K_S | 7.0 GB | 20.4 GB | Too big | Get file → | |
| Q4_K_M | 7.4 GB | 20.8 GB | Too big | Get file → | |
| Q5_K_S | 8.3 GB | 21.7 GB | Too big | Get file → | |
| Q5_K_M | 8.5 GB | 21.9 GB | Too big | Get file → | |
| Q6_K | 9.8 GB | 23.2 GB | Too big | Get file → | |
| Q8_0 | 12.7 GB | 26.1 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (7.38 GB file, ~20.8 GB memory at 8k context). For 12 GB VRAM, Q5_K_M (8.55 GB file, ~21.9 GB memory) offers higher fidelity. For 16 GB VRAM, Q6_K (9.79 GB file, ~23.2 GB memory) provides a balance between size and quality.
What GPU do you need for SuperGemma 4 12b 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 Q6_K (9.8 GB file, about 23.2 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_0 (12.7 GB file, about 26.1 GB in use).
Which SuperGemma 4 12b Abliterated quant should you choose?
Q4_K_M is the usual starting point for SuperGemma 4 12b Abliterated: it balances file size and quality well. Here it is a 7.4 GB file.
The Q8_0 file is 12.7 GB, about 1.7 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 4.8 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
Source
Frequently asked questions about SuperGemma 4 12b Abliterated
How much VRAM does SuperGemma 4 12b Abliterated need?
About 20.8 GB at Q4_K_M with an 8K context window. That is the 7.4 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 SuperGemma 4 12b Abliterated on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 18.2 GB, so you would need a larger GPU or CPU offloading.
What is the file size of SuperGemma 4 12b Abliterated GGUF?
It depends on the quant: Q2_K is 4.8 GB, Q3_K_S is 5.5 GB, Q3_K_M is 6.1 GB, Q3_K_L is 6.6 GB, IQ4_XS is 6.7 GB, Q4_K_S is 7.0 GB and 5 more.
What context length does SuperGemma 4 12b 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 12.9 GB at 8K and 51.5 GB at 32K.
Where can I download SuperGemma 4 12b Abliterated GGUF?
The files are on Hugging Face in the mradermacher/SuperGemma-4-12b-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 SuperGemma 4 12b Abliterated 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 SuperGemma 4 12b Abliterated on 8 GB VRAM?
Use the Q4_K_M quant; it requires approximately 20.8 GB memory at 8k context, so 8 GB VRAM is insufficient. Consider a lower‑precision quant like Q2_K if memory is limited.
Does this model support vision tasks?
Yes, the model has detected vision abilities, but it is not a dedicated vision model and may require additional configuration.
What license applies to this model?
The model is released under the Apache‑2.0 license.