MI

MiniCPM V 4.7 1B Heretic

MiniCPMGGUF by mradermacherUpdated 2026-10-16
Download on Hugging Face
Parameters1.01B
Context256K
Layers25
Architectureqwen35
Smallest quant0.5 GB
Quick answer

MiniCPM V 4.7 1B Heretic 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 12 quants, from 0.5 GB (Q2_K) to 2.0 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.7 GB.

MiniCPM V 4.7 1B Heretic – a small, fully multimodal GGUF model

MiniCPM V 4.7 1B Heretic is a 1.01B parameter text tower with an additional 0.55B vision tower, totaling 1.55B parameters. The GGUF format includes a separate 1.11 GB projector for vision. It supports reasoning, roleplay, tools, and vision tasks.

Good at

  • Multimodal reasoning
  • OCR and visual grounding
  • On‑device image Q&A

Limits

  • Requires both text and projector files for vision
  • Limited to 262,144 context tokens
  • No external vision libraries needed

Best for

  • Local image question answering
  • Document reading and OCR
  • Visual grounding in mobile agents

Who it’s for. Developers needing a compact, uncensored vision‑language model that runs on phones or low‑VRAM devices. The model is ideal for on‑device image processing and local vision agents.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K0.5 GB 1.4 GB
Fits Get file →
Q3_K_S0.5 GB 1.5 GB
Fits Get file →
Q3_K_M0.6 GB 1.5 GB
Fits Get file →
Q3_K_L0.6 GB 1.5 GB
Fits Get file →
IQ4_XS0.6 GB 1.6 GB
Fits Get file →
Q4_K_S0.6 GB 1.6 GB
Fits Get file →
Q4_K_M0.7 GB 1.6 GB
Fits Get file →
Q5_K_S0.7 GB 1.7 GB
Fits Get file →
Q5_K_M0.8 GB 1.7 GB
Fits Get file →
Q6_K0.8 GB 1.8 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 (file size 0.67 GB, ~1.6 GB VRAM at 8 k context). If you have 4 GB VRAM, choose Q3_K_S (0.54 GB, ~1.5 GB VRAM). For the smallest footprint, Q2_K (0.51 GB, ~1.4 GB VRAM) is recommended. Estimates are approximate.

What GPU do you need for MiniCPM V 4.7 1B Heretic?

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 Heretic quant should you choose?

Q4_K_M is the usual starting point for MiniCPM V 4.7 1B Heretic: 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.

If memory is tight, the smallest file is Q2_K at 0.5 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

Architectureqwen35
Parameters1.01B
Layers25
Trained context262,144 tokens
KV cache (fp16)50 KB per token

Source

Quantized bymradermacher
FamilyMiniCPM
Licenseapache-2.0
Downloads (HF)1,099
Last updated2026-10-16

Frequently asked questions about MiniCPM V 4.7 1B Heretic

How much VRAM does MiniCPM V 4.7 1B Heretic 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 Heretic 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 Heretic GGUF?

It depends on the quant: Q2_K is 0.5 GB, Q3_K_S is 0.5 GB, Q3_K_M is 0.6 GB, Q3_K_L is 0.6 GB, IQ4_XS is 0.6 GB, Q4_K_S is 0.6 GB and 6 more.

What context length does MiniCPM V 4.7 1B Heretic 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 1.7 GB at 32K.

Where can I download MiniCPM V 4.7 1B Heretic GGUF?

The files are on Hugging Face in the mradermacher/MiniCPM-V-4.7-1B-heretic-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 Heretic 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 Heretic on 8 GB VRAM?

Yes, using the Q4_K_M quant (0.67 GB file) plus the 1.11 GB projector will fit within 8 GB VRAM, with about 1.6 GB used for the model and 1.11 GB for the projector.

Do I need to load a separate projector file for vision?

Yes. The vision tower is shipped as MiniCPM-V-4.7-1B-heretic-mmproj-F16.gguf (1.11 GB). Both files must be loaded for image input.

Is the model licensed for commercial use?

The model is released under the apache-2.0 license, which permits commercial use.

Other GGUFs of MiniCPM-V-4.7-1B-heretic

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More MiniCPM models

All MiniCPM →

Other tiny models

All tiny models →