MI

MiniCPM V 4.6 Abliterated AND Disinhibited

MiniCPMGGUF by treadonUpdated 2026-05-12
Download on Hugging Face
Parameters752M
Context256K
Layers24
Architectureqwen35
Smallest quant0.5 GB
Quick answer

MiniCPM V 4.6 Abliterated AND Disinhibited needs about 1.4 GB of memory at Q4_K_M (a 0.5 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 1.6 GB.

MiniCPM V 4.6 Abliterated AND Disinhibited – a small, multimodal LLM

MiniCPM V 4.6 Abliterated AND Disinhibited is a 0.752 billion‑parameter model based on Qwen3.5‑0.8B and SigLIP2‑400M. It supports reasoning, tools, and vision tasks while removing neutrality and refusal behaviors. The model is available in GGUF format with a Q4_K_M quantization.

Good at

  • Reasoning and multimodal queries
  • Tool use and instruction following
  • Vision‑language understanding

Limits

  • Requires ~1.4 GB VRAM at 8 k context
  • No separate vision model – vision is integrated
  • Apache‑2.0 license limits commercial redistribution

Best for

  • Mobile on‑device inference
  • Low‑latency vision‑language apps
  • Educational demos

Who it’s for. Developers and researchers who need a compact multimodal model for edge deployment. The model is suitable for Android, iOS, and HarmonyOS platforms and can be fine‑tuned with llama.cpp or other frameworks.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M0.5 GB 1.4 GB
Fits Get file →

For 8 GB VRAM, the Q4_K_M quantized file (0.53 GB) is recommended. It uses approximately 1.4 GB of VRAM at 8 k context. If memory is tighter, consider a higher‑compression quantization if available, but it is not listed here.

What GPU do you need for MiniCPM V 4.6 Abliterated AND Disinhibited?

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 Q4_K_M (0.5 GB file, about 1.4 GB in use).

Which MiniCPM V 4.6 Abliterated AND Disinhibited quant should you choose?

Q4_K_M is the usual starting point for MiniCPM V 4.6 Abliterated AND Disinhibited: it balances file size and quality well. Here it is a 0.5 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35
Parameters752M
Layers24
Trained context262,144 tokens
KV cache (fp16)48 KB per token

Source

Quantized bytreadon
FamilyMiniCPM
Licenseapache-2.0
Downloads (HF)721
Last updated2026-05-12

Frequently asked questions about MiniCPM V 4.6 Abliterated AND Disinhibited

How much VRAM does MiniCPM V 4.6 Abliterated AND Disinhibited need?

About 1.4 GB at Q4_K_M with an 8K context window. That is the 0.5 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 MiniCPM V 4.6 Abliterated AND Disinhibited on an 8 GB GPU?

Yes, with Q4_K_M: the 0.5 GB file needs about 1.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of MiniCPM V 4.6 Abliterated AND Disinhibited GGUF?

It depends on the quant: Q4_K_M is 0.5 GB.

What context length does MiniCPM V 4.6 Abliterated AND Disinhibited support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.4 GB at 8K and 1.6 GB at 32K.

Where can I download MiniCPM V 4.6 Abliterated AND Disinhibited GGUF?

The files are on Hugging Face in the treadon/MiniCPM-V-4.6-Abliterated-AND-Disinhibited repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does MiniCPM V 4.6 Abliterated AND Disinhibited 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 this model on 8 GB VRAM?

Yes, the Q4_K_M quantized file uses about 1.4 GB of VRAM at 8 k context, fitting comfortably on 8 GB.

Does it support vision tasks?

Yes, the model includes vision capabilities integrated with the Qwen3.5 backbone.

What license applies?

The model is released under the Apache‑2.0 license, allowing commercial use with attribution.

Other GGUFs of MiniCPM-V-4.6

Similar models

Browse all →

More MiniCPM models

All MiniCPM →

Other tiny models

All tiny models →