MI

MiniCPM4 0.5B

MiniCPMGGUF by mradermacherUpdated 2025-06-07
Download on Hugging Face
Parameters434M
Context32K
Layers24
Architectureminicpm
Smallest quant0.2 GB
Quick answer

MiniCPM4 0.5B needs about 0.9 GB of memory at Q4_K_M (a 0.3 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 12 quants, from 0.2 GB (Q2_K) to 0.9 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 0.4 GB.

MiniCPM4 0.5B – compact 0.5B parameter LLM for edge devices

MiniCPM4 0.5B is a 0.5B parameter language model trained on 1T tokens. It supports a 32768 token context window and is released under the apache-2.0 license. The model is available in multiple GGUF quantizations for efficient inference.

Good at

  • Fast decoding on low‑end GPUs
  • Small file size for quick download
  • Low VRAM footprint

Limits

  • No vision capabilities
  • Requires explicit add_special_tokens in vLLM chat API
  • Limited to 32768 token context

Best for

  • Edge device inference
  • Rapid prototyping
  • Low‑budget deployment

Who it’s for. Developers building lightweight language applications on devices with limited memory. Researchers needing a small, open‑licensed model for experimentation.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K0.2 GB 0.8 GB
Fits Get file →
Q3_K_S0.2 GB 0.8 GB
Fits Get file →
Q3_K_M0.2 GB 0.8 GB
Fits Get file →
Q3_K_L0.3 GB 0.9 GB
Fits Get file →
IQ4_XS0.3 GB 0.9 GB
Fits Get file →
Q4_K_S0.3 GB 0.9 GB
Fits Get file →
Q4_K_M0.3 GB 0.9 GB
Fits Get file →
Q5_K_S0.3 GB 0.9 GB
Fits Get file →
Q5_K_M0.3 GB 0.9 GB
Fits Get file →
Q6_K0.4 GB 1.0 GB
Fits Get file →
Q8_00.5 GB 1.1 GB
Fits Get file →
F160.9 GB 1.5 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_M (0.28 GB, 0.9 GB memory) or Q5_K_M (0.32 GB, 0.9 GB memory). For 4 GB VRAM, Q3_K_M (0.24 GB, 0.8 GB memory) or Q3_K_S (0.22 GB, 0.8 GB memory) are suitable. For 2 GB VRAM, Q2_K (0.19 GB, 0.8 GB memory) is the smallest option.

What GPU do you need for MiniCPM4 0.5B?

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 (0.9 GB file, about 1.5 GB in use).

Which MiniCPM4 0.5B quant should you choose?

Q4_K_M is the usual starting point for MiniCPM4 0.5B: it balances file size and quality well. Here it is a 0.3 GB file.

The Q8_0 file is 0.5 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 Q2_K at 0.2 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureminicpm
Parameters434M
Layers24
Trained context32,768 tokens
KV cache (fp16)12 KB per token

Source

Quantized bymradermacher
FamilyMiniCPM
Licenseapache-2.0
Downloads (HF)509
Last updated2025-06-07

Frequently asked questions about MiniCPM4 0.5B

How much VRAM does MiniCPM4 0.5B need?

About 0.9 GB at Q4_K_M with an 8K context window. That is the 0.3 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 MiniCPM4 0.5B on an 8 GB GPU?

Yes, with F16: the 0.9 GB file needs about 1.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of MiniCPM4 0.5B GGUF?

It depends on the quant: Q2_K is 0.2 GB, Q3_K_S is 0.2 GB, Q3_K_M is 0.2 GB, Q3_K_L is 0.3 GB, IQ4_XS is 0.3 GB, Q4_K_S is 0.3 GB and 6 more.

What context length does MiniCPM4 0.5B support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.1 GB at 8K and 0.4 GB at 32K.

Where can I download MiniCPM4 0.5B GGUF?

The files are on Hugging Face in the mradermacher/MiniCPM4-0.5B-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 MiniCPM4 0.5B 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 MiniCPM4 0.5B on a GPU with 4 GB VRAM?

Yes, the Q3_K_M quant uses 0.24 GB file size and requires approximately 0.8 GB VRAM at 8k context.

Does the model support vision inputs?

No, MiniCPM4 0.5B is a text‑only model.

What license applies to this model?

The model is released under the apache-2.0 license.

Other GGUFs of MiniCPM4-0.5B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More MiniCPM models

All MiniCPM →

Other tiny models

All tiny models →