MiniCPM V 4 — Hardware Requirements & GPU Compatibility
Vision
MiniCPM-V 4.0 is OpenBMB's 4.1-billion-parameter multimodal model, built on SigLIP2-400M and MiniCPM4-3B and designed for on-device use. It handles single-image, multi-image and video understanding, and the card reports an OpenCompass average of 69.0, ahead of MiniCPM-V 2.6 at 8.1 billion parameters and Qwen2.5-VL-3B-Instruct. The card also reports under two seconds to first token and more than 17 tokens per second on an iPhone 16 Pro Max. At this size it runs on modest consumer GPUs, laptops and even phones once quantized. Context length is 32,768 tokens. It is released under the Apache 2.0 license, permitting commercial and research use, and was published in July 2025. It is the efficiency-focused successor to MiniCPM-V 2.6, and the card lists support for llama.cpp, Ollama, vLLM and SGLang.
48.8K downloads
464 likesSpecifications
- Publisher
- OpenBMB
- Family
- MiniCPM
- Parameters
- 4.1B
- Architecture
- MiniCPMV
- Context Length
- 32,768 tokens
- Vocabulary Size
- 73,448
- Release Date
- 2025-07-12
- License
- Apache 2.0
Get Started
HuggingFace
How Much VRAM Does MiniCPM V 4 Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_Kest. | 3.40 | 2.1 GB | 2.7 GB | 1.73 GB | 2-bit quantization with K-quant improvements |
| Q3_K_Mest. | 3.90 | 2.3 GB | 3.0 GB | 1.98 GB | 3-bit medium quantization |
| Q4_0 | 4.00 | 2.4 GB | 3 GB | 2.03 GB | 4-bit legacy quantization |
| Q4_K_M | 4.80 | 2.8 GB | 3.4 GB | 2.44 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_M | 5.70 | 3.2 GB | 3.9 GB | 2.89 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_K | 6.60 | 3.7 GB | 4.3 GB | 3.35 GB | 6-bit quantization, very good quality |
| Q8_0 | 8.00 | 4.4 GB | 5.0 GB | 4.06 GB | 8-bit quantization, near-lossless |
est.= calculated VRAM estimate; no published GGUF file found for that quantization yet. Other rows are verified against real community uploads.
Which GPUs Can Run MiniCPM V 4?
Q4_K_M · 2.8 GBMiniCPM V 4 (Q4_K_M) requires 2.8 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 4+ GB is recommended. Using the full 33K context window can add up to 0.6 GB, bringing total usage to 3.4 GB. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti.
Runs great
— Plenty of headroomWhich Devices Can Run MiniCPM V 4?
Q4_K_M · 2.8 GB59 devices with unified memory can run MiniCPM V 4, including NVIDIA DGX H100, NVIDIA DGX A100 640GB.
Runs great
— Plenty of headroomWhere to Download MiniCPM V 4
Community quantizations of this model — GGUF for llama.cpp, Ollama, and LM Studio, plus AWQ/MLX variants where available.
Related Models
Frequently Asked Questions
- How much VRAM does MiniCPM V 4 need?
MiniCPM V 4 requires 2.8 GB of VRAM at Q4_K_M, or 8.5 GB at BF16. Full 33K context adds up to 0.6 GB (3.4 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 4.1B × 4.8 bits ÷ 8 = 2.4 GB
KV Cache + Overhead ≈ 0.4 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 1 GB (at full 33K context)
VRAM usage by quantization
Q4_K_M2.8 GBQ4_K_M + full context3.4 GB- What's the best quantization for MiniCPM V 4?
For MiniCPM V 4, Q4_K_M (2.8 GB) offers the best balance of quality and VRAM usage. Q5_0 (2.9 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 2.1 GB.
VRAM requirement by quantization
Q2_K2.1 GBQ4_K_S2.6 GBQ4_K_M ★2.8 GBQ5_02.9 GBQ5_K_M3.2 GBBF168.5 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run MiniCPM V 4 on a Mac?
MiniCPM V 4 requires at least 2.1 GB at Q2_K, which exceeds the unified memory of most consumer Macs. You would need a Mac Studio or Mac Pro with a high-memory configuration.
- Can I run MiniCPM V 4 locally?
Yes — MiniCPM V 4 can run locally on consumer hardware. At Q4_K_M quantization it needs 2.8 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is MiniCPM V 4?
At Q4_K_M, MiniCPM V 4 can reach ~1727 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~236 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: NVIDIA B200 → 8000 ÷ 2.8 × 0.65 = ~1871 tok/s
Estimated speed at Q4_K_M (2.8 GB)
~1871 tok/s~236 tok/s~1871 tok/s~1727 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of MiniCPM V 4?
At Q4_K_M, the download is about 2.44 GB. The full-precision BF16 version is 8.12 GB. The smallest option (Q2_K) is 1.73 GB.
- Which GPUs can run MiniCPM V 4?
52 consumer GPUs can run MiniCPM V 4 at Q4_K_M (2.8 GB). Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT. 52 GPUs have plenty of headroom for comfortable inference.
- Which devices can run MiniCPM V 4?
59 devices with unified memory can run MiniCPM V 4 at Q4_K_M (2.8 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Apple iPhone 17 Pro, Asus ROG Flow Z13 (2025, Ryzen AI Max+ 395, 128 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.