LL

minicpm 2b sft bf16 llamafied 16k

LlamaGGUF by babybirdprdUpdated 2024-02-18
Download on Hugging Face
Parameters3.01B
Context16K
Layers40
Architecturellama
Smallest quant2.0 GB
Quick answer

minicpm 2b sft bf16 llamafied 16k needs about 5.5 GB of memory at BF16 (a 2.0 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 2 quants, from 2.0 GB (BF16) to 2.2 GB (BF16).

minicpm 2b sft bf16 llamafied 16k is a 3.01B-parameter Llama model in GGUF format, quantized by babybirdprd. Its trained context length is 16K tokens. The repository has 2 quant files, from 2.0 GB (BF16) to 2.2 GB (BF16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
BF162.0 GB 5.5 GB
Fits Get file →
BF162.2 GB 5.8 GB
Fits Get file →

What GPU do you need for minicpm 2b sft bf16 llamafied 16k?

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 BF16 (2.2 GB file, about 5.8 GB in use).

Which minicpm 2b sft bf16 llamafied 16k quant should you choose?

BF16 (2.0 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
Parameters3.01B
Layers40
Trained context16,384 tokens
KV cache (fp16)360 KB per token

Source

Quantized bybabybirdprd
FamilyLlama
Downloads (HF)70
Last updated2024-02-18

Frequently asked questions about minicpm 2b sft bf16 llamafied 16k

How much VRAM does minicpm 2b sft bf16 llamafied 16k need?

About 5.5 GB at BF16 with an 8K context window. That is the 2.0 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 minicpm 2b sft bf16 llamafied 16k on an 8 GB GPU?

Yes, with BF16: the 2.2 GB file needs about 5.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of minicpm 2b sft bf16 llamafied 16k GGUF?

It depends on the quant: BF16 is 2.0 GB, BF16 is 2.2 GB.

What context length does minicpm 2b sft bf16 llamafied 16k support?

The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 3.0 GB at 8K and 6.0 GB at 16K.

Where can I download minicpm 2b sft bf16 llamafied 16k GGUF?

The files are on Hugging Face in the babybirdprd/minicpm-2b-sft-bf16-llamafied-16k-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

More from babybirdprd

All by babybirdprd →

More Llama models

All Llama →

Other tiny models

All tiny models →