PH

KimLan phi 2 zh

PhiGGUF by elliotthwangUpdated 2024-01-08
Download on Hugging Face
Parameters2.78B
Context2K
Layers32
Architecturephi2
Smallest quant1.8 GB
Quick answer

KimLan phi 2 zh needs about 5.0 GB of memory at Q4_K_M (a 1.8 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 3 quants, from 1.8 GB (Q4_K_M) to 3.0 GB (Q8_0).

KimLan phi 2 zh is a 2.78B-parameter Phi model in GGUF format, quantized by elliotthwang. Its trained context length is 2K tokens. The repository has 3 quant files, from 1.8 GB (Q4_K_M) to 3.0 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M1.8 GB 3.0 GB
Fits Get file →
Q5_K_M2.1 GB 3.2 GB
Fits Get file →
Q8_03.0 GB 4.1 GB
Fits Get file →

What GPU do you need for KimLan phi 2 zh?

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 Q5_K_M (2.1 GB file, about 5.3 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (3.0 GB file, about 6.1 GB in use).

Which KimLan phi 2 zh quant should you choose?

Q4_K_M is the usual starting point for KimLan phi 2 zh: it balances file size and quality well. Here it is a 1.8 GB file.

The Q8_0 file is 3.0 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

Architecturephi2
Parameters2.78B
Layers32
Trained context2,048 tokens
KV cache (fp16)320 KB per token

Source

Quantized byelliotthwang
FamilyPhi
Downloads (HF)31
Last updated2024-01-08

Frequently asked questions about KimLan phi 2 zh

How much VRAM does KimLan phi 2 zh need?

About 5.0 GB at Q4_K_M 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 KimLan phi 2 zh on an 8 GB GPU?

Yes, with Q8_0: the 3.0 GB file needs about 6.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of KimLan phi 2 zh GGUF?

It depends on the quant: Q4_K_M is 1.8 GB, Q5_K_M is 2.1 GB, Q8_0 is 3.0 GB.

What context length does KimLan phi 2 zh support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 2.7 GB at 8K and 0.7 GB at 2K.

Where can I download KimLan phi 2 zh GGUF?

The files are on Hugging Face in the elliotthwang/KimLan_phi-2_zh.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 elliotthwang

All by elliotthwang →

More Phi models

All Phi →

Other tiny models

All tiny models →