MI

MiniCPM5 1B Agentic Tooluse v3

MiniCPMGGUF by ewin-regUpdated 2026-07-29
Download on Hugging Face
Parameters1.08B
Context128K
Layers24
Architecturellama
Smallest quant0.7 GB
Quick answer

MiniCPM5 1B Agentic Tooluse v3 needs about 1.4 GB of memory at Q4_K_M (a 0.7 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 3 quants, from 0.7 GB (Q4_K_M) to 2.2 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 0.8 GB.

MiniCPM5 1B Agentic Tooluse v3 – a 1B‑parameter function‑calling LLM for local use

MiniCPM5 1B Agentic Tooluse v3 is a 1‑billion‑parameter Llama‑style model fine‑tuned for tool calling. It runs entirely offline on CPU or GPU and supports long‑context up to 131,072 tokens. The model is released under Apache‑2.0 and is available in multiple GGUF quantizations.

Good at

  • Tool‑calling with high exact‑argument accuracy
  • Long‑context reasoning up to 131,072 tokens
  • Local deployment on CPU or low‑VRAM GPU

Limits

  • No vision support
  • Requires 8,000‑token context for memory estimates
  • No GPU required but performance improves with GPU

Best for

  • Offline function‑calling agents
  • Raspberry Pi or laptop assistants
  • Private local AI agents

Who it’s for. Developers building local assistants or agents that need reliable tool‑calling without cloud access. It is also suitable for hobbyists on low‑end hardware who want a private, cost‑free function‑calling model.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M0.7 GB 1.4 GB
Fits Get file →
Q8_01.2 GB 1.9 GB
Fits Get file →
F162.2 GB 2.9 GB
Fits Get file →

For 8 GB VRAM use Q4_K_M (file size 0.69 GB, estimated 1.4 GB memory). For 12 GB VRAM use Q8_0 (1.15 GB, 1.9 GB memory). If more memory is available, F16 (2.17 GB, 2.9 GB memory) gives the highest precision.

What GPU do you need for MiniCPM5 1B Agentic Tooluse v3?

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 (2.2 GB file, about 2.9 GB in use).

Which MiniCPM5 1B Agentic Tooluse v3 quant should you choose?

Q4_K_M is the usual starting point for MiniCPM5 1B Agentic Tooluse v3: it balances file size and quality well. Here it is a 0.7 GB file.

The Q8_0 file is 1.2 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
Parameters1.08B
Layers24
Trained context131,072 tokens
KV cache (fp16)24 KB per token

Source

Quantized byewin-reg
FamilyMiniCPM
Licenseapache-2.0
Downloads (HF)3,151
Last updated2026-07-29

Frequently asked questions about MiniCPM5 1B Agentic Tooluse v3

How much VRAM does MiniCPM5 1B Agentic Tooluse v3 need?

About 1.4 GB at Q4_K_M with an 8K context window. That is the 0.7 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 1B Agentic Tooluse v3 on an 8 GB GPU?

Yes, with F16: the 2.2 GB file needs about 2.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of MiniCPM5 1B Agentic Tooluse v3 GGUF?

It depends on the quant: Q4_K_M is 0.7 GB, Q8_0 is 1.2 GB, F16 is 2.2 GB.

What context length does MiniCPM5 1B Agentic Tooluse v3 support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.8 GB at 32K.

Where can I download MiniCPM5 1B Agentic Tooluse v3 GGUF?

The files are on Hugging Face in the ewin-reg/MiniCPM5-1B-Agentic-Tooluse-v3-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 1B Agentic Tooluse v3 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 1B Agentic Tooluse v3 on 8 GB VRAM?

Yes, the Q4_K_M quantization requires about 1.4 GB VRAM at 8,000‑token context, which fits within 8 GB.

Does this model support vision or image input?

No, the model is a purely text‑based LLM with no vision capabilities.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Other GGUFs of MiniCPM5-1B

Similar models

Browse all →

More from ewin-reg

All by ewin-reg →

More MiniCPM models

All MiniCPM →

Other tiny models

All tiny models →