MiniCPM o 2 6 needs about 5.7 GB of memory at Q4_K_M (a 4.7 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 10 quants, from 4.4 GB (Q4_0) to 15.2 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.9 GB.
MiniCPM-o 2.6 – a 7.6B parameter multimodal model with vision and speech support
MiniCPM-o 2.6 is a 7.6 billion‑parameter model built on the Qwen2 architecture. It supports vision and speech, with a 32 768‑token context window. The model is released under the Apache‑2.0 license and is available in multiple GGUF quantizations.
Good at
- Vision tasks with 8‑bit quantization
- Speech conversation in English and Chinese
- Multimodal live streaming
Limits
- No text‑only inference without vision
- Requires at least 5 GB VRAM for Q4_0 at 8 k context
- No support for 3‑D or audio‑only modes yet
Best for
- Image captioning on low‑end GPUs
- Real‑time bilingual voice chat
- Live video analysis in streaming apps
Who it’s for. Developers building multimodal applications on edge devices. The model is suitable for projects needing both vision and speech capabilities within a modest memory footprint.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_0 | 4.4 GB | 5.4 GB | Fits | Get file → | |
| Q4_K_S | 4.5 GB | 5.4 GB | Fits | Get file → | |
| Q4_K_M | 4.7 GB | 5.7 GB | Fits | Get file → | |
| Q4_1 | 4.9 GB | 5.8 GB | Fits | Get file → | |
| Q5_0 | 5.3 GB | 6.3 GB | Fits | Get file → | |
| Q5_K_M | 5.4 GB | 6.4 GB | Fits | Get file → | |
| Q5_1 | 5.8 GB | 6.7 GB | Fits | Get file → | |
| Q6_K | 6.3 GB | 7.2 GB | Tight | Get file → | |
| Q8_0 | 8.1 GB | 9.1 GB | Too big | Get file → | |
| F16 | 15.2 GB | 16.2 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_0 or Q4_K_S (≈5.4 GB). If 12 GB VRAM is available, Q4_K_M or Q5_0 provide better quality. For maximum fidelity, Q8_0 or F16 can be used on 16 GB+ VRAM setups.
What GPU do you need for MiniCPM o 2 6?
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: no quant fits at an 8K context.
- 6 GB VRAM: the best quant that fits is Q4_1 (4.9 GB file, about 5.8 GB in use).
- 8 GB VRAM: the best quant that fits is Q6_K (6.3 GB file, about 7.2 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (8.1 GB file, about 9.1 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (8.1 GB file, about 9.1 GB in use).
- 24 GB VRAM: the best quant that fits is F16 (15.2 GB file, about 16.2 GB in use).
Which MiniCPM o 2 6 quant should you choose?
Q4_K_M is the usual starting point for MiniCPM o 2 6: it balances file size and quality well. Here it is a 4.7 GB file.
The Q8_0 file is 8.1 GB, about 1.7 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 Q4_0 at 4.4 GB, with the quality trade-offs that come with fewer bits. 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
Source
Frequently asked questions about MiniCPM o 2 6
How much VRAM does MiniCPM o 2 6 need?
About 5.7 GB at Q4_K_M with an 8K context window. That is the 4.7 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 o 2 6 on an 8 GB GPU?
Yes, with Q6_K: the 6.3 GB file needs about 7.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of MiniCPM o 2 6 GGUF?
It depends on the quant: Q4_0 is 4.4 GB, Q4_K_S is 4.5 GB, Q4_K_M is 4.7 GB, Q4_1 is 4.9 GB, Q5_0 is 5.3 GB, Q5_K_M is 5.4 GB and 4 more.
What context length does MiniCPM o 2 6 support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.5 GB at 8K and 1.9 GB at 32K.
Where can I download MiniCPM o 2 6 GGUF?
The files are on Hugging Face in the openbmb/MiniCPM-o-2_6-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 o 2 6 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-o 2.6 on 8 GB VRAM?
Yes, the Q4_0 or Q4_K_S quantizations use about 5.4 GB at 8 k context, fitting within 8 GB VRAM.
Does the model support text‑only inference?
The current GGUF files only support vision; text‑only usage is not available yet.
What license applies to this model?
The model is released under the Apache‑2.0 license, allowing free use and modification.