MI

MiniCPM5 2B Abliterated iq4XS

MiniCPMGGUF by edgebitesUpdated 2026-10-11
Download on Hugging Face
Parameters2.52B
Context128K
Layers42
Architecturellama
Smallest quant1.3 GB
Quick answer

MiniCPM5 2B Abliterated iq4XS needs about 2.2 GB of memory at IQ4_XS (a 1.3 GB file) with an 8K context window, so it fits on a 4 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 1.4 GB.

MiniCPM5 2B Abliterated IQ4_XS – lightweight reasoning model

MiniCPM5 2B Abliterated IQ4_XS is a 2.52 billion‑parameter model quantized to IQ4_XS. It supports reasoning and tool usage. The model is released under the MIT license and is optimized for local inference with llama.cpp.

Good at

  • Reasoning
  • Tool usage
  • Low KL divergence ablation

Limits

  • No vision support
  • Requires 2.2 GB VRAM at 8k context
  • Single quant available

Best for

  • Local on‑device inference
  • Chat applications
  • Educational demos

Who it’s for. Developers and researchers who need a compact, reasoning‑capable model for local deployment. The MIT license allows free use and modification.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ4_XS1.3 GB 2.2 GB
Fits Get file →

For 8 GB VRAM, use the IQ4_XS quantization (1.34 GB file). It requires about 2.2 GB VRAM at 8k context. No other quants are available for this model.

What GPU do you need for MiniCPM5 2B Abliterated iq4XS?

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 IQ4_XS (1.3 GB file, about 2.2 GB in use).

Which MiniCPM5 2B Abliterated iq4XS quant should you choose?

IQ4_XS (1.3 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters2.52B
Layers42
Trained context131,072 tokens
KV cache (fp16)42 KB per token

Source

Quantized byedgebites
FamilyMiniCPM
Licensemit
Downloads (HF)611
Last updated2026-10-11

Frequently asked questions about MiniCPM5 2B Abliterated iq4XS

How much VRAM does MiniCPM5 2B Abliterated iq4XS need?

About 2.2 GB at IQ4_XS with an 8K context window. That is the 1.3 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 MiniCPM5 2B Abliterated iq4XS on an 8 GB GPU?

Yes, with IQ4_XS: the 1.3 GB file needs about 2.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of MiniCPM5 2B Abliterated iq4XS GGUF?

It depends on the quant: IQ4_XS is 1.3 GB.

What context length does MiniCPM5 2B Abliterated iq4XS 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 Abliterated iq4XS GGUF?

The files are on Hugging Face in the edgebites/MiniCPM5-2B-Abliterated-iq4XS-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 Abliterated iq4XS use?

Hugging Face lists the license as mit. 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 Abliterated IQ4_XS on 8 GB VRAM?

Yes. The IQ4_XS quant uses 1.34 GB file size and needs approximately 2.2 GB VRAM at 8k context.

Does this model support vision tasks?

No, the model has no vision capabilities.

What license applies to this model?

The model is released under the MIT license.

Similar models

Browse all →

More MiniCPM models

All MiniCPM →

Other tiny models

All tiny models →