VibeThinker 3B Heretic_Decensored needs about 2.7 GB of memory at Q4_K_M (a 1.9 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 15 quants, from 1.3 GB (Q2_K) to 12.3 GB (F32). Longer context needs more: at 32K tokens the KV cache alone adds about 1.2 GB.
VibeThinker 3B Heretic_Decensored – a 3B‑parameter reasoning model
VibeThinker 3B Heretic_Decensored is a 3.09‑billion‑parameter language model built on Qwen2.5-Coder-3B. It focuses on mathematics, coding, and STEM reasoning while reducing internal refusal behaviors. The model is released under the apache-2.0 license for research use.
Good at
- Mathematics reasoning
- Code generation
- STEM domain queries
Limits
- No vision support
- Experimental; may produce sensitive content
- Requires research‑grade usage
Best for
- Solving complex math problems
- Writing and debugging code
- Answering technical STEM questions
Who it’s for. Researchers and developers needing a compact reasoning model for math, coding, and STEM tasks. The model is intended for learning and experimentation and should be used responsibly.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 1.3 GB | 2.1 GB | Fits | Get file → | |
| Q3_K_S | 1.5 GB | 2.3 GB | Fits | Get file → | |
| Q3_K_M | 1.6 GB | 2.4 GB | Fits | Get file → | |
| Q3_K_L | 1.7 GB | 2.5 GB | Fits | Get file → | |
| Q4_0 | 1.8 GB | 2.6 GB | Fits | Get file → | |
| Q4_K_S | 1.8 GB | 2.6 GB | Fits | Get file → | |
| Q4_K_M | 1.9 GB | 2.7 GB | Fits | Get file → | |
| Q5_0 | 2.2 GB | 3.0 GB | Fits | Get file → | |
| Q5_K_S | 2.2 GB | 3.0 GB | Fits | Get file → | |
| Q5_K_M | 2.2 GB | 3.0 GB | Fits | Get file → | |
| Q6_K | 2.5 GB | 3.3 GB | Fits | Get file → | |
| Q8_0 | 3.3 GB | 4.1 GB | Fits | Get file → | |
| BF16 | 6.2 GB | 7.0 GB | Fits | Get file → | |
| F16 | 6.2 GB | 7.0 GB | Fits | Get file → | |
| F32 | 12.3 GB | 13.2 GB | Too big | Get file → |
For 8 k context, Q4_K_M (1.93 GB) uses about 2.7 GB of VRAM, Q5_K_M (2.22 GB) about 3 GB, and Q6_K (2.54 GB) about 3.3 GB. Choose the smallest quant that fits your VRAM budget; higher‑precision quants like F16 or BF16 need 7 GB.
What GPU do you need for VibeThinker 3B Heretic_Decensored?
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 3.3 GB in use).
- 6 GB VRAM: the best quant that fits is Q8_0 (3.3 GB file, about 4.1 GB in use).
- 8 GB VRAM: the best quant that fits is BF16 (6.2 GB file, about 7.0 GB in use).
- 12 GB VRAM: the best quant that fits is BF16 (6.2 GB file, about 7.0 GB in use).
- 16 GB VRAM: the best quant that fits is F32 (12.3 GB file, about 13.2 GB in use).
Which VibeThinker 3B Heretic_Decensored quant should you choose?
Q4_K_M is the usual starting point for VibeThinker 3B Heretic_Decensored: it balances file size and quality well. Here it is a 1.9 GB file.
The Q8_0 file is 3.3 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 1.3 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 VibeThinker 3B Heretic_Decensored
How much VRAM does VibeThinker 3B Heretic_Decensored need?
About 2.7 GB at Q4_K_M with an 8K context window. That is the 1.9 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 VibeThinker 3B Heretic_Decensored on an 8 GB GPU?
Yes, with BF16: the 6.2 GB file needs about 7.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of VibeThinker 3B Heretic_Decensored GGUF?
It depends on the quant: Q2_K is 1.3 GB, Q3_K_S is 1.5 GB, Q3_K_M is 1.6 GB, Q3_K_L is 1.7 GB, Q4_0 is 1.8 GB, Q4_K_S is 1.8 GB and 9 more.
What context length does VibeThinker 3B Heretic_Decensored support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.3 GB at 8K and 1.2 GB at 32K.
Where can I download VibeThinker 3B Heretic_Decensored GGUF?
The files are on Hugging Face in the prithivMLmods/VibeThinker-3B-heretic_decensored-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 VibeThinker 3B Heretic_Decensored 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 VibeThinker 3B Heretic_Decensored on 8 GB VRAM?
Yes, using Q4_K_M or Q5_K_M quants will fit within 8 GB VRAM, with memory usage around 2.7–3 GB at 8 k context.
Does this model support image inputs?
No, the model has no vision capabilities and only processes text.
Is the model safe for production use?
The model is experimental and may generate unrestricted content; it is intended strictly for research and learning purposes.