PH

medisynth phi 3.5 mini instruct 8192 dev

PhiGGUF by abhinandUpdated 2024-08-24
Download on Hugging Face
Parameters3.82B
Context128K
Layers—
Architecturellama
Smallest quant2.3 GB
Quick answer

medisynth phi 3.5 mini instruct 8192 dev needs about 3.1 GB of memory at Q4_K_M (a 2.3 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 4 quants, from 2.3 GB (Q4_K_M) to 7.6 GB (BF16).

medisynth phi 3.5 mini instruct 8192 dev is a 3.82B-parameter Phi model in GGUF format, quantized by abhinand. Its trained context length is 128K tokens. The repository has 4 quant files, from 2.3 GB (Q4_K_M) to 7.6 GB (BF16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M2.3 GB 3.1 GB
Fits Get file →
Q5_K_M2.7 GB 3.5 GB
Fits Get file →
Q8_04.1 GB 5.0 GB
Fits Get file →
BF167.6 GB 9.1 GB
Too big Get file →

What GPU do you need for medisynth phi 3.5 mini instruct 8192 dev?

These figures add the file size, an fp16 KV cache at an 8K context window 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 Q5_K_M (2.7 GB file, about 3.5 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (4.1 GB file, about 5.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (4.1 GB file, about 5.0 GB in use).
  • 12 GB VRAM: the best quant that fits is BF16 (7.6 GB file, about 9.1 GB in use).

Which medisynth phi 3.5 mini instruct 8192 dev quant should you choose?

Q4_K_M is the usual starting point for medisynth phi 3.5 mini instruct 8192 dev: 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
Trained context131,072 tokens

Source

Quantized byabhinand
FamilyPhi
Licenseapache-2.0
Downloads (HF)0
Last updated2024-08-24

Frequently asked questions about medisynth phi 3.5 mini instruct 8192 dev

How much VRAM does medisynth phi 3.5 mini instruct 8192 dev need?

About 3.1 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 medisynth phi 3.5 mini instruct 8192 dev on an 8 GB GPU?

Yes, with Q8_0: the 4.1 GB file needs about 5.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of medisynth phi 3.5 mini instruct 8192 dev 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 medisynth phi 3.5 mini instruct 8192 dev support?

The GGUF header lists a trained context length of 131,072 tokens (128K).

Where can I download medisynth phi 3.5 mini instruct 8192 dev GGUF?

The files are on Hugging Face in the abhinand/medisynth-phi-3.5-mini-instruct-8192-dev-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 medisynth phi 3.5 mini instruct 8192 dev 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.

Other GGUFs of Phi-3.5-mini-instruct

Similar models

Browse all →

More from abhinand

All by abhinand →

More Phi models

All Phi →

Other small models

All small models →