MI

minicpm dpo bf16 ggml model q4 0

MiniCPMGGUF by openbmbUpdated 2024-02-08
Download on Hugging Face
Parameters3.01B
Context2K
Layers40
Architecturellama
Smallest quant1.8 GB
Quick answer

minicpm dpo bf16 ggml model q4 0 needs about 5.3 GB of memory at Q4_0 (a 1.8 GB file) with an 8K context window, so it fits on a 6 GB GPU.

minicpm dpo bf16 ggml model q4 0 is a 3.01B-parameter MiniCPM model in GGUF format, quantized by openbmb. Its trained context length is 2K tokens. The repository has 1 quant file, from 1.8 GB (Q4_0) to 1.8 GB (Q4_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_01.8 GB 3.0 GB
Fits Get file →

What GPU do you need for minicpm dpo bf16 ggml model q4 0?

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 Q4_0 (1.8 GB file, about 5.3 GB in use).

Which minicpm dpo bf16 ggml model q4 0 quant should you choose?

Q4_0 (1.8 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters3.01B
Layers40
Trained context2,048 tokens
KV cache (fp16)360 KB per token

Source

Quantized byopenbmb
FamilyMiniCPM
Licenseapache-2.0
Downloads (HF)43
Last updated2024-02-08

Frequently asked questions about minicpm dpo bf16 ggml model q4 0

How much VRAM does minicpm dpo bf16 ggml model q4 0 need?

About 5.3 GB at Q4_0 with an 8K context window. That is the 1.8 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 minicpm dpo bf16 ggml model q4 0 on an 8 GB GPU?

Yes, with Q4_0: the 1.8 GB file needs about 5.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of minicpm dpo bf16 ggml model q4 0 GGUF?

It depends on the quant: Q4_0 is 1.8 GB.

What context length does minicpm dpo bf16 ggml model q4 0 support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 3.0 GB at 8K and 0.8 GB at 2K.

Where can I download minicpm dpo bf16 ggml model q4 0 GGUF?

The files are on Hugging Face in the openbmb/minicpm-dpo-bf16-ggml-model-q4_0 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does minicpm dpo bf16 ggml model q4 0 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.

Similar models

Browse all →

More from openbmb

All by openbmb →

More MiniCPM models

All MiniCPM →

Other tiny models

All tiny models →