MiniCPM V 4.6 Heretic 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. This repository has 12 quants, from 0.4 GB (Q2_K) to 1.5 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.
MiniCPM V 4.6 Heretic – a compact multimodal model for image and video understanding
MiniCPM V 4.6 Heretic is a 0.752 billion‑parameter model built on qwen35 architecture. It supports vision tasks and is optimized for edge deployment. The model is available in multiple GGUF quantizations for low‑memory inference.
Good at
- Efficient image and video understanding
- Low‑memory inference on consumer GPUs
- Support for mixed 4x/16x visual token compression
Limits
- No text‑only inference without vision
- Requires at least 1.3 GB VRAM for 8 k context
- No support for large context beyond 262144 tokens
Best for
- Mobile on‑device image analysis
- Lightweight video captioning
- Rapid prototyping of multimodal apps
Who it’s for. Developers building mobile or edge applications that need both vision and language capabilities in a small footprint. Researchers wanting a reproducible, open‑source multimodal model for experimentation.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 0.4 GB | 1.3 GB | Fits | Get file → | |
| Q3_K_S | 0.4 GB | 1.3 GB | Fits | Get file → | |
| Q3_K_M | 0.5 GB | 1.4 GB | Fits | Get file → | |
| Q3_K_L | 0.5 GB | 1.4 GB | Fits | Get file → | |
| Q4_K_S | 0.5 GB | 1.4 GB | Fits | Get file → | |
| IQ4_XS | 0.5 GB | 1.4 GB | Fits | Get file → | |
| Q4_K_M | 0.5 GB | 1.4 GB | Fits | Get file → | |
| Q5_K_S | 0.6 GB | 1.5 GB | Fits | Get file → | |
| Q5_K_M | 0.6 GB | 1.5 GB | Fits | Get file → | |
| Q6_K | 0.6 GB | 1.5 GB | Fits | Get file → | |
| Q8_0 | 0.8 GB | 1.7 GB | Fits | Get file → | |
| F16 | 1.5 GB | 2.4 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K (0.53 GB file, ~1.4 GB memory) or Q5_K_S (0.56 GB file, ~1.5 GB memory). For tighter budgets, Q2_K (0.42 GB file, ~1.3 GB memory) is suitable. Larger models like F16 (1.52 GB file, ~2.4 GB memory) provide higher precision when memory allows.
What GPU do you need for MiniCPM V 4.6 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 (1.5 GB file, about 2.4 GB in use).
Which MiniCPM V 4.6 Heretic quant should you choose?
Q4_K_M is the usual starting point for MiniCPM V 4.6 Heretic: it balances file size and quality well. Here it is a 0.5 GB file.
The Q8_0 file is 0.8 GB, about 1.5 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 0.4 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
Source
Frequently asked questions about MiniCPM V 4.6 Heretic
How much VRAM does MiniCPM V 4.6 Heretic 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 Heretic on an 8 GB GPU?
Yes, with F16: the 1.5 GB file needs about 2.4 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 Heretic GGUF?
It depends on the quant: Q2_K is 0.4 GB, Q3_K_S is 0.4 GB, Q3_K_M is 0.5 GB, Q3_K_L is 0.5 GB, Q4_K_S is 0.5 GB, IQ4_XS is 0.5 GB and 6 more.
What context length does MiniCPM V 4.6 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 1.6 GB at 32K.
Where can I download MiniCPM V 4.6 Heretic GGUF?
The files are on Hugging Face in the mradermacher/MiniCPM-V-4.6-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 4.6 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 4.6 Heretic on 8 GB VRAM?
Yes, the Q4_K quantization uses about 1.4 GB VRAM at 8 k context, fitting comfortably on 8 GB GPUs.
Does the model support text‑only inference?
The model is primarily vision‑enabled; text‑only inference is not its focus and may lack full functionality.
What license applies to this model?
The model is released under the apache-2.0 license.