MI

MiniCPM5 2B

MiniCPMGGUF by Atomic-GermUpdated 2026-09-14
Download on Hugging Face
Parameters2.52B
Context128K
Layers42
Architecturellama
Smallest quant0.0 GB
Quick answer

MiniCPM5 2B needs about 2.4 GB of memory at Q4_K_M (a 1.6 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 5 quants, from 0.0 GB to 1.8 GB (Q5_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 1.4 GB.

MiniCPM5 2B – a 2.52B‑parameter dense transformer for local deployment

MiniCPM5 2B is a 2.52B‑parameter dense transformer trained on 131072‑token context. It is optimized for on‑device inference and resource‑constrained scenarios. The model supports coding, reasoning, and tool use.

Good at

  • Coding tasks
  • Long‑context reasoning
  • Tool integration

Limits

  • Requires 8k context for memory estimates
  • No vision support
  • Apache‑2.0 license

Best for

  • Local code generation
  • Long‑form document analysis
  • Agentic task execution

Who it’s for. Developers and researchers needing a compact, open‑source model for local inference. It is suitable for edge devices and environments with limited GPU memory.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 0.9 GB
Fits Get file →
IQ4_NL1.5 GB 2.3 GB
Fits Get file →
Q4_K_M1.6 GB 2.4 GB
Fits Get file →
Q4_11.6 GB 2.5 GB
Fits Get file →
Q5_K_M1.8 GB 2.7 GB
Fits Get file →

For 8k context, Q4_K_M (1.56 GB file, 2.4 GB memory) is a good balance of size and speed. If memory is tighter, Q4_1 (1.63 GB, 2.5 GB) or IQ4_NL (1.49 GB, 2.3 GB) can be used. For the smallest file, use IQ4_NL but expect slightly higher memory usage.

What GPU do you need for MiniCPM5 2B?

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 Q5_K_M (1.8 GB file, about 2.7 GB in use).

Which MiniCPM5 2B quant should you choose?

Q4_K_M is the usual starting point for MiniCPM5 2B: it balances file size and quality well. Here it is a 1.6 GB file.

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

Architecturellama
Parameters2.52B
Layers42
Trained context131,072 tokens
KV cache (fp16)42 KB per token

Source

Quantized byAtomic-Germ
FamilyMiniCPM
Licenseapache-2.0
Downloads (HF)661
Last updated2026-09-14

Frequently asked questions about MiniCPM5 2B

How much VRAM does MiniCPM5 2B need?

About 2.4 GB at Q4_K_M with an 8K context window. That is the 1.6 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 MiniCPM5 2B on an 8 GB GPU?

Yes, with Q5_K_M: the 1.8 GB file needs about 2.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of MiniCPM5 2B GGUF?

It depends on the quant: file is 0.0 GB, IQ4_NL is 1.5 GB, Q4_K_M is 1.6 GB, Q4_1 is 1.6 GB, Q5_K_M is 1.8 GB.

What context length does MiniCPM5 2B support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.4 GB at 8K and 1.4 GB at 32K.

Where can I download MiniCPM5 2B GGUF?

The files are on Hugging Face in the Atomic-Germ/MiniCPM5-2B-OpenNPU2 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does MiniCPM5 2B 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 MiniCPM5 2B on 8 GB VRAM?

Yes, using Q4_K_M or IQ4_NL the model uses about 2.4 GB of VRAM at 8k context, leaving room for other processes.

Does MiniCPM5 2B support coding?

Yes, the model is trained for coding tasks and includes tool‑use capabilities.

Other GGUFs of MiniCPM5-2B

Similar models

Browse all →

More from Atomic-Germ

All by Atomic-Germ →

More MiniCPM models

All MiniCPM →

Other tiny models

All tiny models →