Ollama · minicpm-v4.5

<img src="/assets/openbmb/minicpm-v2.6/452bfaf1-53f4-4485-8a92-e4a1a05abf38" alt="MiniCPM-V.png" width="50%" style="display:block; margin:auto;"> <h1>A GPT-4o Level MLLM for Single Image, Multi Image…

ollama/minicpm-v4.5

<img src="/assets/openbmb/minicpm-v2.6/452bfaf1-53f4-4485-8a92-e4a1a05abf38" alt="MiniCPM-V.png" width="50%" style="display:block; margin:auto;">

<h1>A GPT-4o Level MLLM for Single Image, Multi Image and High-FPS Video Understanding on Your Phone</h1>

<p align="center"> MiniCPM-V 4.5 <a href="https://huggingface.co/openbmb/MiniCPM-V-4_5">🤗</a> <a href="http://101.126.42.235:30910/">🤖</a> | MiniCPM-o 2.6 <a href="https://huggingface.co/openbmb/MiniCPM-o-2_6">🤗</a> <a href="https://minicpm-omni-webdemo-us.modelbest.cn/"> 🤖</a> | 🍳 <a href="https://github.com/OpenSQZ/MiniCPM-V-Cookbook">Cookbook</a> | 📄 <a href="https://arxiv.org/abs/2509.18154">Technical Report</a> </p>

**MiniCPM-V 4.5** is the latest and most capable model in the MiniCPM-V series. The model is built on Qwen3-8B and SigLIP2-400M with a total of 8B parameters. It exhibits a significant performance improvement over previous MiniCPM-V and MiniCPM-o models, and introduces new useful features. Notable features of MiniCPM-V 4.5 include:

- 🔥 **State-of-the-art Vision-Language Capability.** MiniCPM-V 4.5 achieves an average score of 77.2 on OpenCompass, a comprehensive evaluation of 8 popular benchmarks. **With only 8B parameters, it surpasses widely used proprietary models like GPT-4o-latest, Gemini-2.0 Pro, and strong open-source models like Qwen2.5-VL 72B** for vision-language capabilities, making it the most performant MLLM under 30B parameters.

- 🎬 **Efficient High Refresh Rate and Long Video Understanding.** Powered by a new unified 3D-Resampler over images and videos, MiniCPM-V 4.5 can now achieve 96x compression rate for video tokens, where 6 448x448 video frames can be jointly compressed into 64 video tokens (normally 1,536 tokens for most MLLMs). This means that the model can percieve significantly more video frames without increasing the LLM inference cost. This brings state-of-the-art high refresh rate (up to 10FPS) video understanding and long video understanding capabilities on Video-MME, LVBench, MLVU, MotionBench, FavorBench, etc., efficiently.

- ⚙️ **Controllable Hybrid Fast/Deep Thinking.** MiniCPM-V 4.5 supports both fast thinking for efficient frequent usage with competitive performance, and deep thinking for more complex problem solving. To cover efficiency and performance trade-offs in different user scenarios, this fast/deep thinking mode can be switched in a highly controlled fashion.

- 💪 **Strong OCR, Document Parsing and Others.** Based on [LLaVA-UHD](https://arxiv.org/pdf/2403.11703) architecture, MiniCPM-V 4.5 can process high-resolution images with any aspect ratio and up to 1.8 million pixels (e.g., 1344x1344), using 4x less visual tokens than most MLLMs. The model achieves **leading performance on OCRBench, surpassing proprietary models such as GPT-4o-latest and Gemini 2.5**. It also achieves state-of-the-art performance for PDF document parsing capability on OmniDocBench among general MLLMs. Based on the the latest [RLAIF-V](https://github.com/RLHF-V/RLAIF-V/) and [VisCPM](https://github.com/OpenBMB/VisCPM) techniques, it features **trustworthy behaviors**, outperforming GPT-4o-latest on MMHal-Bench, and supports **multilingual capabilities** in more than 30 languages.

- 💫 **Easy Usage.** MiniCPM-V 4.5 can be easily used in various ways: (1) [llama.cpp](https://github.com/tc-mb/llama.cpp/blob/Support-MiniCPM-V-4.5/docs/multimodal/minicpmv4.5.md) and [ollama](https://github.com/tc-mb/ollama/tree/MIniCPM-V) support for efficient CPU inference on local devices, (2) [int4](https://huggingface.co/openbmb/MiniCPM-V-4_5-int4), [GGUF](https://huggingface.co/openbmb/MiniCPM-V-4_5-gguf) and [AWQ](https://github.com/tc-mb/AutoAWQ) format quantized models in 16 sizes, (3) [SGLang](https://github.com/tc-mb/sglang/tree/main) and [vLLM](#efficient-inference-with-llamacpp-ollama-vllm) support for high-throughput and memory-efficient inference, (4) fine-tuning on new domains and tasks with [Transformers](https://github.com/tc-mb/transformers/tree/main) and [LLaMA-Factory](./docs/llamafactory_train_and_infer.md), (5) quick [local WebUI demo](#chat-with-our-demo-on-gradio), (6) optimized [local iOS app](https://github.com/tc-mb/MiniCPM-o-demo-iOS) on iPhone and iPad, and (7) online web demo on [server](http://101.126.42.235:30910/). See our [Cookbook](https://github.com/OpenSQZ/MiniCPM-V-CookBook) for full usages!

> [!NOTE] > If you have any questions, please feel free to submit an issue here: > [MiniCPM-V Issues](https://github.com/OpenBMB/MiniCPM-V/issues). We will actively > respond to all questions from the community.

Specifications & capabilities

Published model ID
minicpm-v4.5

Deployments & artifacts

1–13 / 13

ollama

source id
ollama
execution mode
local
parameter size
8.2B
parameter count
8200000000
parameter count is approximate
true
quantization level
Q4_K_M
context window
40000
context window is approximate
true
artifact size bytes
6121827520
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
8.2B
parameter count
8200000000
parameter count is approximate
true
quantization level
F16
context window
40000
context window is approximate
true
artifact size bytes
17480072256
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
8.2B
parameter count
8200000000
parameter count is approximate
true
quantization level
Q4_K_M
context window
40000
context window is approximate
true
artifact size bytes
6121827520
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
8.2B
parameter count
8200000000
parameter count is approximate
true
quantization level
Q4_0
context window
40000
context window is approximate
true
artifact size bytes
5868793024
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
8.2B
parameter count
8200000000
parameter count is approximate
true
quantization level
Q4_1
context window
40000
context window is approximate
true
artifact size bytes
6341750976
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
8.2B
parameter count
8200000000
parameter count is approximate
true
quantization level
Q4_K_M
context window
40000
context window is approximate
true
artifact size bytes
6121827520
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
8.2B
parameter count
8200000000
parameter count is approximate
true
quantization level
Q4_K_S
context window
40000
context window is approximate
true
artifact size bytes
5896056000
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
8.2B
parameter count
8200000000
parameter count is approximate
true
quantization level
Q5_0
context window
40000
context window is approximate
true
artifact size bytes
6814708928
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
8.2B
parameter count
8200000000
parameter count is approximate
true
quantization level
Q5_1
context window
40000
context window is approximate
true
artifact size bytes
7287666880
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
8.2B
parameter count
8200000000
parameter count is approximate
true
quantization level
Q5_K_M
context window
40000
context window is approximate
true
artifact size bytes
6945060032
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
8.2B
parameter count
8200000000
parameter count is approximate
true
quantization level
Q5_K_S
context window
40000
context window is approximate
true
artifact size bytes
6814708928
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
8.2B
parameter count
8200000000
parameter count is approximate
true
quantization level
Q6_K
context window
40000
context window is approximate
true
artifact size bytes
7819744576
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
8.2B
parameter count
8200000000
parameter count is approximate
true
quantization level
Q8_0
context window
40000
context window is approximate
true
artifact size bytes
9802990656
updated at
2026-11-16T08:10:06.079865+00:00

Original sources

1–2 / 2

Ollama · Model page ↗

Ollama · Catalog ↗

Source links

1–1 / 1

Explore more models

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace