MiniCPM5 2B heretic abliterated needs about 2.4 GB of memory at Q4_K_M (a 1.6 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 6 quants, from 1.3 GB (Q3_K_M) to 2.7 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 1.4 GB.
MiniCPM5 2B heretic abliterated – a 2.5B‑parameter LLM for local inference
MiniCPM5 2B heretic abliterated is a 2.5‑billion‑parameter dense transformer built for on‑device deployment. It retains the original MiniCPM5‑2B capabilities while removing refusal behavior via directional ablation. The model supports up to 131,072 context tokens and is released under Apache‑2.0.
Good at
- Strong coding and math reasoning
- Long‑context understanding
- Tool and agentic task performance
Limits
- No vision support
- Requires at least 8 GB VRAM for Q4_K_M
- License is Apache‑2.0
Best for
- Local code generation
- Complex math problem solving
- Agentic workflows on limited hardware
Who it’s for. Developers and researchers needing a compact, open‑source LLM for local inference. The model is suitable for edge devices and applications where privacy and offline operation are priorities.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_M | 1.3 GB | 2.1 GB | Fits | Get file → | |
| Q4_K_S | 1.5 GB | 2.4 GB | Fits | Get file → | |
| Q4_K_M | 1.6 GB | 2.4 GB | Fits | Get file → | |
| Q5_K_M | 1.8 GB | 2.7 GB | Fits | Get file → | |
| Q6_K | 2.1 GB | 2.9 GB | Fits | Get file → | |
| Q8_0 | 2.7 GB | 3.5 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_M (1.56 GB file, ~2.4 GB VRAM at 8 k context). If 12 GB VRAM is available, Q5_K_M (1.81 GB, ~2.7 GB VRAM) offers higher precision. Q6_K (2.07 GB) is suitable for 16 GB VRAM setups.
What GPU do you need for MiniCPM5 2B 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 Q8_0 (2.7 GB file, about 3.5 GB in use).
Which MiniCPM5 2B heretic abliterated quant should you choose?
Q4_K_M is the usual starting point for MiniCPM5 2B heretic abliterated: it balances file size and quality well. Here it is a 1.6 GB file.
The Q8_0 file is 2.7 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 Q3_K_M at 1.3 GB, with the quality trade-offs that come with fewer bits. 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 MiniCPM5 2B heretic abliterated
How much VRAM does MiniCPM5 2B heretic abliterated need?
About 2.4 GB at Q4_K_M with an 8K context window. That is the 1.6 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 MiniCPM5 2B heretic abliterated on an 8 GB GPU?
Yes, with Q8_0: the 2.7 GB file needs about 3.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of MiniCPM5 2B heretic abliterated GGUF?
It depends on the quant: Q3_K_M is 1.3 GB, Q4_K_S is 1.5 GB, Q4_K_M is 1.6 GB, Q5_K_M is 1.8 GB, Q6_K is 2.1 GB, Q8_0 is 2.7 GB.
What context length does MiniCPM5 2B 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 1.4 GB at 32K.
Where can I download MiniCPM5 2B heretic abliterated GGUF?
The files are on Hugging Face in the Abiray/MiniCPM5-2B-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 MiniCPM5 2B 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 MiniCPM5 2B heretic abliterated on 8 GB VRAM?
Yes, the Q4_K_M quantization requires about 2.4 GB VRAM at 8 k context, which fits within an 8 GB GPU.
Does this model support image inputs?
No, the model has no vision capability.
What license applies to this model?
The model is released under the Apache‑2.0 license.