PH

ChemGist Phi3 Q4 K M

PhiGGUF by JAZLUpdated 2026-04-27
Download on Hugging Face
Parameters3.82B
Context4K
Layers—
Architecturellama
Smallest quant2.3 GB
Quick answer

ChemGist Phi3 Q4 K M 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.

ChemGist Phi3 Q4 K M is a 3.82B-parameter Phi model in GGUF format, quantized by JAZL. Its trained context length is 4K tokens. The repository has 1 quant file, from 2.3 GB (Q4_K_M) to 2.3 GB (Q4_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M2.3 GB 3.0 GB
Fits Get file →

What GPU do you need for ChemGist Phi3 Q4 K M?

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 Q4_K_M (2.3 GB file, about 3.1 GB in use).

Which ChemGist Phi3 Q4 K M quant should you choose?

Q4_K_M is the usual starting point for ChemGist Phi3 Q4 K M: it balances file size and quality well. Here it is a 2.3 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters3.82B
Trained context4,096 tokens

Source

Quantized byJAZL
FamilyPhi
Licenseapache-2.0
Downloads (HF)0
Last updated2026-04-27

Frequently asked questions about ChemGist Phi3 Q4 K M

How much VRAM does ChemGist Phi3 Q4 K M 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 ChemGist Phi3 Q4 K M on an 8 GB GPU?

Yes, with Q4_K_M: the 2.3 GB file needs about 3.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of ChemGist Phi3 Q4 K M GGUF?

It depends on the quant: Q4_K_M is 2.3 GB.

What context length does ChemGist Phi3 Q4 K M support?

The GGUF header lists a trained context length of 4,096 tokens (4K).

Where can I download ChemGist Phi3 Q4 K M GGUF?

The files are on Hugging Face in the JAZL/ChemGist-Phi3-Q4_K_M-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 ChemGist Phi3 Q4 K M 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 ChemGist-Phi3

Similar models

Browse all →

More from JAZL

All by JAZL →

More Phi models

All Phi →

Other small models

All small models →