G9v3 3B Heretic Abliterated needs about 2.8 GB of memory at Q4_K_M (a 1.8 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 33 quants, from 0.6 GB (Q1_0) to 12.0 GB (F32). Longer context needs more: at 32K tokens the KV cache alone adds about 1.7 GB.
3B causal language model, uncensored, tool‑use ready
G9v3 3B Heretic Abliterated is a 3B parameter Llama‑style model with a 131,072 token context. It is a heretic ablated variant, removing built‑in refusal behavior for broader prompt compliance. The model is released under Apache‑2.0 and is suited for local, resource‑constrained deployment.
Good at
- Tool‑use workflows
- Compact assistant tasks
- Reasoning with long context
Limits
- No vision support
- Uncensored build requires downstream safety
- Large VRAM needed for higher quants
Best for
- Local chatbot with tool integration
- Coding assistance on modest GPUs
- Long‑form reasoning in offline setups
Who it’s for. Developers and researchers who need a small, local LLM that can handle tool‑use and long‑context tasks without the overhead of a larger model. The uncensored build is for users who will implement their own safety layers.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q1_0 | 0.6 GB | 1.5 GB | Fits | Get file → | |
| IQ1_S | 0.8 GB | 1.7 GB | Fits | Get file → | |
| IQ1_M | 0.8 GB | 1.8 GB | Fits | Get file → | |
| TQ1_0 | 0.9 GB | 1.8 GB | Fits | Get file → | |
| IQ2_XXS | 0.9 GB | 1.9 GB | Fits | Get file → | |
| IQ2_XS | 1.0 GB | 1.9 GB | Fits | Get file → | |
| TQ2_0 | 1.0 GB | 1.9 GB | Fits | Get file → | |
| IQ2_S | 1.1 GB | 2.0 GB | Fits | Get file → | |
| Q2_0 | 1.1 GB | 2.0 GB | Fits | Get file → | |
| IQ2_M | 1.1 GB | 2.1 GB | Fits | Get file → | |
| Q2_K | 1.2 GB | 2.1 GB | Fits | Get file → | |
| IQ3_XXS | 1.2 GB | 2.2 GB | Fits | Get file → | |
| IQ3_XS | 1.3 GB | 2.3 GB | Fits | Get file → | |
| Q3_K_S | 1.4 GB | 2.3 GB | Fits | Get file → | |
| IQ3_S | 1.4 GB | 2.3 GB | Fits | Get file → | |
| IQ3_M | 1.4 GB | 2.4 GB | Fits | Get file → | |
| Q3_K_M | 1.5 GB | 2.5 GB | Fits | Get file → | |
| Q3_K_L | 1.6 GB | 2.6 GB | Fits | Get file → | |
| IQ4_XS | 1.7 GB | 2.6 GB | Fits | Get file → | |
| Q4_0 | 1.8 GB | 2.7 GB | Fits | Get file → | |
| Q4_K_S | 1.8 GB | 2.7 GB | Fits | Get file → | |
| IQ4_NL | 1.8 GB | 2.7 GB | Fits | Get file → | |
| Q4_K_M | 1.8 GB | 2.8 GB | Fits | Get file → | |
| Q4_1 | 1.9 GB | 2.9 GB | Fits | Get file → | |
| Q5_0 | 2.1 GB | 3.0 GB | Fits | Get file → | |
| Q5_K_S | 2.1 GB | 3.0 GB | Fits | Get file → | |
| Q5_K_M | 2.1 GB | 3.1 GB | Fits | Get file → | |
| Q5_1 | 2.3 GB | 3.2 GB | Fits | Get file → | |
| Q6_K | 2.5 GB | 3.4 GB | Fits | Get file → | |
| Q8_0 | 3.2 GB | 4.1 GB | Fits | Get file → | |
| BF16 | 6.0 GB | 6.9 GB | Fits | Get file → | |
| F16 | 6.0 GB | 6.9 GB | Fits | Get file → | |
| F32 | 12.0 GB | 12.9 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (1.84 GB file, ~2.8 GB memory at 8k context). If 4 GB VRAM is available, Q3_K_M (1.52 GB file, ~2.5 GB memory) is the largest practical quant. For the best quality on 12 GB VRAM, Q6_K (2.46 GB file, ~3.4 GB memory) is recommended.
What GPU do you need for G9v3 3B Heretic 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: the best quant that fits is Q6_K (2.5 GB file, about 3.4 GB in use).
- 6 GB VRAM: the best quant that fits is Q8_0 (3.2 GB file, about 4.1 GB in use).
- 8 GB VRAM: the best quant that fits is BF16 (6.0 GB file, about 6.9 GB in use).
- 12 GB VRAM: the best quant that fits is BF16 (6.0 GB file, about 6.9 GB in use).
- 16 GB VRAM: the best quant that fits is F32 (12.0 GB file, about 12.9 GB in use).
Which G9v3 3B Heretic Abliterated quant should you choose?
Q4_K_M is the usual starting point for G9v3 3B Heretic Abliterated: it balances file size and quality well. Here it is a 1.8 GB file.
The Q8_0 file is 3.2 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 Q1_0 at 0.6 GB, with the quality trade-offs that come with fewer bits. Lower bit counts mean smaller files and more quality loss.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about G9v3 3B Heretic Abliterated
How much VRAM does G9v3 3B Heretic Abliterated need?
About 2.8 GB at Q4_K_M with an 8K context window. That is the 1.8 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 G9v3 3B Heretic Abliterated on an 8 GB GPU?
Yes, with BF16: the 6.0 GB file needs about 6.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of G9v3 3B Heretic Abliterated GGUF?
It depends on the quant: Q1_0 is 0.6 GB, IQ1_S is 0.8 GB, IQ1_M is 0.8 GB, TQ1_0 is 0.9 GB, IQ2_XXS is 0.9 GB, IQ2_XS is 1.0 GB and 27 more.
What context length does G9v3 3B Heretic 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 0.4 GB at 8K and 1.7 GB at 32K.
Where can I download G9v3 3B Heretic Abliterated GGUF?
The files are on Hugging Face in the Vortecks/G9v3-3B-Heretic-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 G9v3 3B Heretic 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 G9v3 3B Heretic Abliterated on 8 GB VRAM?
Yes, a Q4_K_M quantization fits within 8 GB VRAM, using about 2.8 GB of memory at 8k context.
Does this model support image inputs?
No, it is a purely text‑based causal language model.
Is the model safe for production use?
The uncensored build lacks built‑in refusal behavior; users must implement their own safety and moderation.