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 4 quants, from 4.1 GB (Q3_K_L) to 8.1 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 1.9 GB.
MiniCPM O 2_6 – a 7.61B parameter multimodal LLM
MiniCPM O 2_6 is a 7.61B parameter model built on the Qwen2 architecture. It supports vision, speech, and multimodal live streaming with a 32,768 token context window. The model is available in several GGUF quantizations.
Good at
- Vision tasks with up to 1.8 million pixels
- Real‑time bilingual speech conversation
- Multimodal live streaming
Limits
- No license information provided
- No explicit vision or audio limits beyond pixel count
- No mention of text‑only usage
Best for
- Developers building multimodal apps
- Researchers testing vision‑speech integration
- Users needing real‑time streaming AI
Who it’s for. The model is suited for developers and researchers who require a compact multimodal LLM that can handle images, audio, and live video streams. It is ideal for building applications that need real‑time speech and vision capabilities without large infrastructure.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_L | 4.1 GB | 5.1 GB | Fits | Get file → | |
| Q4_K_M | 4.7 GB | 5.7 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 → |
For 8 GB VRAM use Q4_K_M (4.68 GB file, 5.7 GB memory). For 12 GB VRAM use Q6_K (6.25 GB file, 7.2 GB memory). For 16 GB VRAM use Q8_0 (8.1 GB file, 9.1 GB memory). Estimates are approximate.
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_K_M (4.7 GB file, about 5.7 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).
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 Q3_K_L at 4.1 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
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: Q3_K_L is 4.1 GB, Q4_K_M is 4.7 GB, Q6_K is 6.3 GB, Q8_0 is 8.1 GB.
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 lmstudio-community/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.
Can I run MiniCPM O 2_6 on 8 GB VRAM?
Yes, the Q4_K_M quantization requires about 5.7 GB of VRAM at 8 k context, which fits in an 8 GB GPU.
Does the model support image input?
Yes, it accepts images of any aspect ratio up to 1.8 million pixels.
What context length does the model support?
The model supports a context length of 32,768 tokens.