MI

MiniCPM V 4.7 1B Balanced Heretic Abliterated

MiniCPMGGUF by maternionUpdated 2026-10-17
Download on Hugging Face
Parameters1.01B
Context256K
Layers24
Architectureqwen35
Smallest quant0.7 GB
Quick answer

MiniCPM V 4.7 1B Balanced Heretic Abliterated needs about 1.6 GB of memory at Q4_K_M (a 0.7 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 4 quants, from 0.7 GB (Q4_K_M) to 2.0 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.

MiniCPM‑V 4.7 1B Balanced Heretic Abliterated – a 1B vision‑enabled LLM

MiniCPM‑V 4.7 1B Balanced Heretic Abliterated is a 1.01 billion‑parameter model built on the qwen35 architecture. It supports single‑image, multi‑image, and video understanding with efficient visual encoding. The model is released under Apache‑2.0 and is available in several GGUF quantizations.

Good at

  • Vision‑enabled text generation
  • Efficient on‑device inference
  • Low‑refusal behavior

Limits

  • No explicit language list
  • Requires 8 k context for memory estimates
  • No specialized vision hardware needed

Best for

  • Mobile on‑device image captioning
  • Local video summarization
  • Low‑latency multimodal chat

Who it’s for. Developers building multimodal applications on mobile or edge devices. The model is suitable for those who need vision capabilities with a small memory footprint and low refusal rates.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M0.7 GB 1.6 GB
Fits Get file →
Q6_K0.8 GB 1.7 GB
Fits Get file →
Q8_01.1 GB 2.0 GB
Fits Get file →
F162.0 GB 2.9 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_M (0.67 GB file, ~1.6 GB memory at 8 k context). If 16 GB VRAM is available, Q6_K (0.84 GB, ~1.7 GB) or Q8_0 (1.08 GB, ~2 GB) can be used. The F16 variant (2.02 GB, ~2.9 GB) requires more memory but offers higher precision.

What GPU do you need for MiniCPM V 4.7 1B Balanced 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 F16 (2.0 GB file, about 2.9 GB in use).

Which MiniCPM V 4.7 1B Balanced Heretic Abliterated quant should you choose?

Q4_K_M is the usual starting point for MiniCPM V 4.7 1B Balanced Heretic Abliterated: it balances file size and quality well. Here it is a 0.7 GB file.

The Q8_0 file is 1.1 GB, about 1.6 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.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35
Parameters1.01B
Layers24
Trained context262,144 tokens
KV cache (fp16)48 KB per token

Source

Quantized bymaternion
FamilyMiniCPM
Licenseapache-2.0
Downloads (HF)1,700
Last updated2026-10-17

Frequently asked questions about MiniCPM V 4.7 1B Balanced Heretic Abliterated

How much VRAM does MiniCPM V 4.7 1B Balanced Heretic Abliterated need?

About 1.6 GB at Q4_K_M with an 8K context window. That is the 0.7 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 4.7 1B Balanced Heretic Abliterated on an 8 GB GPU?

Yes, with F16: the 2.0 GB file needs about 2.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of MiniCPM V 4.7 1B Balanced Heretic Abliterated GGUF?

It depends on the quant: Q4_K_M is 0.7 GB, Q6_K is 0.8 GB, Q8_0 is 1.1 GB, F16 is 2.0 GB.

What context length does MiniCPM V 4.7 1B Balanced Heretic Abliterated 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 4.7 1B Balanced Heretic Abliterated GGUF?

The files are on Hugging Face in the maternion/MiniCPM-V-4.7-1B-Balanced-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 MiniCPM V 4.7 1B Balanced 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 MiniCPM‑V 4.7 1B on 8 GB VRAM?

Yes, the Q4_K_M quantization requires about 1.6 GB of VRAM at 8 k context, which fits within an 8 GB budget.

Does this model support image input?

Yes, it works with the base model's vision projector (mmproj) and fully supports image input.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Other GGUFs of MiniCPM-V-4.7-1B

Similar models

Browse all →

More from maternion

All by maternion →

More MiniCPM models

All MiniCPM →

Other tiny models

All tiny models →