MiniCPM o 4 5 needs about 6.7 GB of memory at Q4_K_M (a 5.0 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 20 quants, from 0.0 GB to 16.4 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.
MiniCPM‑o 4.5 – 8.2 B‑parameter multimodal model with vision, speech, and live streaming
MiniCPM‑o 4.5 is an 8.2 B‑parameter model built on Qwen3 architecture. It supports vision, speech, and full‑duplex multimodal live streaming. The model is released under Apache‑2.0 and is available in multiple GGUF quantizations.
Good at
- Vision‑language tasks
- Real‑time speech conversation
- Full‑duplex live streaming
Limits
- No vision support in quantized variants below Q4_0
- Requires at least 6 GB VRAM for Q4_0
- Large context length of 40960 tokens may need more RAM
Best for
- Multimodal chatbots
- Live video‑audio assistants
- OCR and high‑resolution image processing
Who it’s for. Developers building multimodal assistants that need vision, speech, and real‑time interaction. The model is suitable for edge devices with sufficient VRAM and for cloud deployments that can handle 8‑token context sizes.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 1.7 GB | Fits | Get file → | |
| F16 | 0.0 GB | 1.7 GB | Fits | Get file → | |
| — | 0.1 GB | 1.8 GB | Fits | Get file → | |
| — | 0.2 GB | 1.9 GB | Fits | Get file → | |
| — | 0.2 GB | 1.9 GB | Fits | Get file → | |
| — | 0.5 GB | 2.2 GB | Fits | Get file → | |
| F16 | 0.7 GB | 2.4 GB | Fits | Get file → | |
| F16 | 1.1 GB | 2.8 GB | Fits | Get file → | |
| F16 | 1.2 GB | 2.9 GB | Fits | Get file → | |
| Q4_0 | 4.8 GB | 6.5 GB | Fits | Get file → | |
| Q4_K_S | 4.8 GB | 6.5 GB | Fits | Get file → | |
| Q4_K_M | 5.0 GB | 6.7 GB | Fits | Get file → | |
| Q4_1 | 5.2 GB | 7.0 GB | Fits | Get file → | |
| Q5_0 | 5.7 GB | 7.4 GB | Tight | Get file → | |
| Q5_K_S | 5.7 GB | 7.4 GB | Tight | Get file → | |
| Q5_K_M | 5.8 GB | 7.6 GB | Tight | Get file → | |
| Q5_1 | 6.2 GB | 7.9 GB | Tight | Get file → | |
| Q6_K | 6.7 GB | 8.4 GB | Too big | Get file → | |
| Q8_0 | 8.7 GB | 10.4 GB | Too big | Get file → | |
| F16 | 16.4 GB | 18.1 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_0 (4.77 GB file, ~6.5 GB memory). For 12 GB VRAM, Q5_0 (5.72 GB file, ~7.4 GB memory) is a good balance. If more VRAM is available, Q6_K (6.72 GB file, ~8.4 GB memory) offers higher precision.
What GPU do you need for MiniCPM o 4 5?
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 (1.2 GB file, about 2.9 GB in use).
- 6 GB VRAM: the best quant that fits is F16 (1.2 GB file, about 2.9 GB in use).
- 8 GB VRAM: the best quant that fits is Q5_1 (6.2 GB file, about 7.9 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (8.7 GB file, about 10.4 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (8.7 GB file, about 10.4 GB in use).
- 24 GB VRAM: the best quant that fits is F16 (16.4 GB file, about 18.1 GB in use).
Which MiniCPM o 4 5 quant should you choose?
Q4_K_M is the usual starting point for MiniCPM o 4 5: it balances file size and quality well. Here it is a 5.0 GB file.
The Q8_0 file is 8.7 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 the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about MiniCPM o 4 5
How much VRAM does MiniCPM o 4 5 need?
About 6.7 GB at Q4_K_M with an 8K context window. That is the 5.0 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 4 5 on an 8 GB GPU?
Yes, with Q5_1: the 6.2 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of MiniCPM o 4 5 GGUF?
It depends on the quant: file is 0.0 GB, F16 is 0.0 GB, file is 0.1 GB, file is 0.2 GB, file is 0.2 GB, file is 0.5 GB and 14 more.
What context length does MiniCPM o 4 5 support?
The GGUF header lists a trained context length of 40,960 tokens (40K). The KV cache grows with the context you use: about 1.2 GB at 8K and 4.8 GB at 32K.
Where can I download MiniCPM o 4 5 GGUF?
The files are on Hugging Face in the openbmb/MiniCPM-o-4_5-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 4 5 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 4.5 on 8 GB VRAM?
Yes, the Q4_0 quantization requires about 6.5 GB VRAM at 8 k context, which fits within an 8 GB budget.
Does the model support vision?
Yes, the model has detected vision capability and can process high‑resolution images up to 1.8 million pixels.
What license does the model use?
The model is released under the Apache‑2.0 license.