QU

quan 1.8b chat

QuanGGUF by qnguyen3Updated 2024-01-16
Download on Hugging Face
Parameters1.84B
Context8K
Layers24
Architecturellama
Smallest quant1.2 GB
Quick answer

quan 1.8b chat needs about 3.3 GB of memory at Q4_K_M (a 1.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 1.2 GB (Q4_K_M) to 1.4 GB (Q5_K_M).

quan 1.8b chat is a 1.84B-parameter Quan model in GGUF format, quantized by qnguyen3. Its trained context length is 8K tokens. The repository has 2 quant files, from 1.2 GB (Q4_K_M) to 1.4 GB (Q5_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M1.2 GB 3.3 GB
Fits Get file →
Q5_K_M1.4 GB 3.5 GB
Fits Get file →

What GPU do you need for quan 1.8b chat?

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: the best quant that fits is Q5_K_M (1.4 GB file, about 3.5 GB in use).

Which quan 1.8b chat quant should you choose?

Q4_K_M is the usual starting point for quan 1.8b chat: it balances file size and quality well. Here it is a 1.2 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters1.84B
Layers24
Trained context8,192 tokens
KV cache (fp16)192 KB per token

Source

Quantized byqnguyen3
FamilyQuan
Downloads (HF)21
Last updated2024-01-16

Frequently asked questions about quan 1.8b chat

How much VRAM does quan 1.8b chat need?

About 3.3 GB at Q4_K_M with an 8K context window. That is the 1.2 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 quan 1.8b chat on an 8 GB GPU?

Yes, with Q5_K_M: the 1.4 GB file needs about 3.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of quan 1.8b chat GGUF?

It depends on the quant: Q4_K_M is 1.2 GB, Q5_K_M is 1.4 GB.

What context length does quan 1.8b chat support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 1.6 GB at 8K and 1.6 GB at 8K.

Where can I download quan 1.8b chat GGUF?

The files are on Hugging Face in the qnguyen3/quan-1.8b-chat-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 qnguyen3

All by qnguyen3 →

Other tiny models

All tiny models →