CO

codegen2

CodegenGGUF by prashrexUpdated 2024-03-09
Download on Hugging Face
Parameters1.35B
Context16K
Layers24
Architecturellama
Smallest quant0.8 GB
Quick answer

codegen2 needs about 3.0 GB of memory at Q4_K_M (a 0.9 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 0.8 GB (Q4_0) to 0.9 GB (Q4_K_M).

codegen2 is a 1.35B-parameter Codegen model in GGUF format, quantized by prashrex. Its trained context length is 16K tokens. The repository has 2 quant files, from 0.8 GB (Q4_0) to 0.9 GB (Q4_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_00.8 GB 2.9 GB
Fits Get file →
Q4_K_M0.9 GB 3.0 GB
Fits Get file →

What GPU do you need for codegen2?

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 Q4_K_M (0.9 GB file, about 3.0 GB in use).

Which codegen2 quant should you choose?

Q4_K_M is the usual starting point for codegen2: it balances file size and quality well. Here it is a 0.9 GB file.

If memory is tight, the smallest file is Q4_0 at 0.8 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters1.35B
Layers24
Trained context16,384 tokens
KV cache (fp16)192 KB per token

Source

Quantized byprashrex
FamilyCodegen
Downloads (HF)9
Last updated2024-03-09

Frequently asked questions about codegen2

How much VRAM does codegen2 need?

About 3.0 GB at Q4_K_M with an 8K context window. That is the 0.9 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 codegen2 on an 8 GB GPU?

Yes, with Q4_K_M: the 0.9 GB file needs about 3.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of codegen2 GGUF?

It depends on the quant: Q4_0 is 0.8 GB, Q4_K_M is 0.9 GB.

What context length does codegen2 support?

The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 1.6 GB at 8K and 3.2 GB at 16K.

Where can I download codegen2 GGUF?

The files are on Hugging Face in the prashrex/codegen2 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 prashrex

All by prashrex →

More Codegen models

All Codegen →

Other tiny models

All tiny models →