PH

Phi 3 mini 3.8b 4Bit InstructionTuned Alpaca

PhiGGUF by ChituyiUpdated 2024-07-21
Download on Hugging Face
Parameters3.82B
Context4K
Layers32
Architecturellama
Smallest quant2.3 GB
Quick answer

Phi 3 mini 3.8b 4Bit InstructionTuned Alpaca needs about 6.0 GB of memory at Q4_K_M (a 2.3 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 4 quants, from 2.3 GB (Q4_K_M) to 7.6 GB (BF16).

Phi 3 mini 3.8b 4Bit InstructionTuned Alpaca

Phi 3 mini 3.8b 4Bit InstructionTuned Alpaca is a 3.82 billion parameter model based on the Phi family. It supports a 4096 token context window and is released under the MIT license.

Good at

  • Instruction following
  • Alpaca style tasks
  • Low‑memory inference

Limits

  • No vision support
  • Limited to 4096 token context
  • Requires 8 k context for memory estimates

Best for

  • Chatbots on edge devices
  • Quick prototyping
  • Educational demos

Who it’s for. Developers and researchers who need a lightweight Phi model for instruction‑tuned tasks. The model is suitable for environments with limited GPU memory and no need for vision capabilities.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M2.3 GB 4.4 GB
Fits Get file →
Q5_K_M2.7 GB 4.8 GB
Fits Get file →
Q8_04.1 GB 6.2 GB
Fits Get file →
BF167.6 GB 9.8 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (file size 2.32 GB, memory 6 GB). If 12 GB VRAM is available, Q5_K_M (2.72 GB, 6.4 GB) is a good balance. For 16 GB or more, Q8_0 (4.06 GB, 7.8 GB) offers higher precision.

What GPU do you need for Phi 3 mini 3.8b 4Bit InstructionTuned Alpaca?

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_K_M (2.3 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (4.1 GB file, about 7.8 GB in use).
  • 12 GB VRAM: the best quant that fits is BF16 (7.6 GB file, about 11.4 GB in use).

Which Phi 3 mini 3.8b 4Bit InstructionTuned Alpaca quant should you choose?

Q4_K_M is the usual starting point for Phi 3 mini 3.8b 4Bit InstructionTuned Alpaca: it balances file size and quality well. Here it is a 2.3 GB file.

The Q8_0 file is 4.1 GB, about 1.8 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
Parameters3.82B
Layers32
Trained context4,096 tokens
KV cache (fp16)384 KB per token

Source

Quantized byChituyi
FamilyPhi
Licensemit
Downloads (HF)1,200
Last updated2024-07-21

Frequently asked questions about Phi 3 mini 3.8b 4Bit InstructionTuned Alpaca

How much VRAM does Phi 3 mini 3.8b 4Bit InstructionTuned Alpaca need?

About 6.0 GB at Q4_K_M with an 8K context window. That is the 2.3 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 Phi 3 mini 3.8b 4Bit InstructionTuned Alpaca on an 8 GB GPU?

Yes, with Q8_0: the 4.1 GB file needs about 7.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Phi 3 mini 3.8b 4Bit InstructionTuned Alpaca GGUF?

It depends on the quant: Q4_K_M is 2.3 GB, Q5_K_M is 2.7 GB, Q8_0 is 4.1 GB, BF16 is 7.6 GB.

What context length does Phi 3 mini 3.8b 4Bit InstructionTuned Alpaca support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 3.2 GB at 8K and 1.6 GB at 4K.

Where can I download Phi 3 mini 3.8b 4Bit InstructionTuned Alpaca GGUF?

The files are on Hugging Face in the Chituyi/Phi-3-mini-3.8b-4Bit-InstructionTuned-Alpaca repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Phi 3 mini 3.8b 4Bit InstructionTuned Alpaca use?

Hugging Face lists the license as mit. 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 this model on 8 GB VRAM?

Yes, the Q4_K_M quantization uses about 6 GB of VRAM at 8 k context, fitting within an 8 GB GPU.

Does this model support vision tasks?

No, the model does not include vision capabilities.

What license does this model use?

The model is released under the MIT license.

Similar models

Browse all →

More from Chituyi

All by Chituyi →

More Phi models

All Phi →

Other small models

All small models →