MI

openbmb MiniCPM5 2B MLX GGUF F16

MiniCPMGGUF by sigmanihUpdated 2026-10-30
Download on Hugging Face
Parameters2.52B
Context128K
Layers42
Architecturellama
Smallest quant5.0 GB
Quick answer

openbmb MiniCPM5 2B MLX GGUF F16 needs about 5.9 GB of memory at F16 (a 5.0 GB file) with an 8K context window, so it fits on a 6 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 1.4 GB.

MiniCPM5 2B dense transformer for local, on‑device inference

openbmb MiniCPM5 2B MLX GGUF F16 is a 2.52B‑parameter dense model optimized for local deployment. It supports reasoning and tool use, and is trained on a 131072‑token context window.

Good at

  • Reasoning
  • Tool use
  • Local inference

Limits

  • Requires 5.9GB VRAM at 8k context
  • File size 5.04GB
  • No vision support

Best for

  • On‑device chat
  • Coding assistance
  • Tool‑driven tasks

Who it’s for. Developers and researchers who need a compact, high‑performance LLM that can run entirely on local hardware without external APIs.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F165.0 GB 5.9 GB
Fits Get file →

The only available quant is F16, 5.04GB in size. It needs approximately 5.9GB VRAM at 8k context. For 8GB VRAM setups, F16 is suitable; for lower VRAM, no other quant is available.

What GPU do you need for openbmb MiniCPM5 2B MLX GGUF F16?

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: no quant fits at an 8K context.
  • 6 GB VRAM: the best quant that fits is F16 (5.0 GB file, about 5.9 GB in use).

Which openbmb MiniCPM5 2B MLX GGUF F16 quant should you choose?

F16 (5.0 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

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 bysigmanih
FamilyMiniCPM
Licenseother
Downloads (HF)639
Last updated2026-10-30

Frequently asked questions about openbmb MiniCPM5 2B MLX GGUF F16

How much VRAM does openbmb MiniCPM5 2B MLX GGUF F16 need?

About 5.9 GB at F16 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 openbmb MiniCPM5 2B MLX GGUF F16 on an 8 GB GPU?

Yes, with F16: the 5.0 GB file needs about 5.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of openbmb MiniCPM5 2B MLX GGUF F16 GGUF?

It depends on the quant: F16 is 5.0 GB.

What context length does openbmb MiniCPM5 2B MLX GGUF F16 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 openbmb MiniCPM5 2B MLX GGUF F16 GGUF?

The files are on Hugging Face in the sigmanih/openbmb-MiniCPM5-2B-MLX-GGUF-F16 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does openbmb MiniCPM5 2B MLX GGUF F16 use?

Hugging Face lists the license as other. 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 this model on 8GB VRAM?

Yes, it requires about 5.9GB VRAM at 8k context, so 8GB is sufficient.

Does it support tool use?

Yes, the model has detected tool‑use capability.

Is vision support available?

No, the model does not provide vision capabilities.

Other GGUFs of MiniCPM5-2B-MLX

Similar models

Browse all →

More from sigmanih

All by sigmanih →

More MiniCPM models

All MiniCPM →

Other tiny models

All tiny models →