MI

MiniCPM5 2B Math

MiniCPMGGUF by CaldalisUpdated 2026-10-10
Download on Hugging Face
Parameters2.52B
Context128K
Layers42
Architecturellama
Smallest quant1.6 GB
Quick answer

MiniCPM5 2B Math 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 3 quants, from 1.6 GB (Q4_K_M) to 5.0 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.4 GB.

MiniCPM5 2B Math – a 2.5B dense model for long‑form mathematical reasoning

MiniCPM5‑2B‑Math is a 2.52B parameter model built on MiniCPM5, trained for long‑form math reasoning and proof writing. It supports a native 131072‑token context window and runs on a single consumer GPU or laptop.

Good at

  • Long‑form math reasoning
  • Proof generation
  • High accuracy on AIME and HMMT

Limits

  • No vision support
  • Requires large VRAM for full context
  • Apache‑2.0 license

Best for

  • Solving math contest problems
  • Generating step‑by‑step proofs
  • Running a proof swarm on a laptop

Who it’s for. Engineers and researchers who need a compact math‑specialist model that can run on consumer hardware. It is suitable for developers building proof assistants or educational tools.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M1.6 GB 2.4 GB
Fits Get file →
Q8_02.7 GB 3.5 GB
Fits Get file →
BF165.0 GB 5.9 GB
Fits Get file →

For 8 GB VRAM, use the Q4_K_M quantization (1.56 GB file, ~2.4 GB VRAM at 8K context). If 12 GB VRAM is available, Q8_0 (2.68 GB file, ~3.5 GB VRAM) offers higher precision. BF16 (5.04 GB) requires at least 16 GB VRAM.

What GPU do you need for MiniCPM5 2B Math?

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 Q8_0 (2.7 GB file, about 3.5 GB in use).
  • 6 GB VRAM: the best quant that fits is BF16 (5.0 GB file, about 5.9 GB in use).

Which MiniCPM5 2B Math quant should you choose?

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

The Q8_0 file is 2.7 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.

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 byCaldalis
FamilyMiniCPM
Licenseapache-2.0
Downloads (HF)9,533
Last updated2026-10-10

Frequently asked questions about MiniCPM5 2B Math

How much VRAM does MiniCPM5 2B Math 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 Math on an 8 GB GPU?

Yes, with BF16: 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 MiniCPM5 2B Math GGUF?

It depends on the quant: Q4_K_M is 1.6 GB, Q8_0 is 2.7 GB, BF16 is 5.0 GB.

What context length does MiniCPM5 2B Math 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 Math GGUF?

The files are on Hugging Face in the Caldalis/MiniCPM5-2B-Math-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 MiniCPM5 2B Math 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 Math on 8 GB VRAM?

Yes, using the Q4_K_M quantized file (1.56 GB) will fit within 8 GB VRAM with an estimated 2.4 GB usage at 8K context.

Does the model support vision inputs?

No, the model has no vision capabilities.

What context length does it support?

It supports a native 131072‑token context window.

Other GGUFs of MiniCPM5-2B-Math

Similar models

Browse all →

More MiniCPM models

All MiniCPM →

Other tiny models

All tiny models →