RE

replit-code-v1_5-3b

ReplitGGUF by tzhenghaoUpdated 2024-07-10
Download on Hugging Face
Parameters3.32B
Context4K
Layers32
Architecturempt
Smallest quant6.6 GB
Quick answer

replit-code-v1_5-3b needs about 8.2 GB of memory at BF16 (a 6.6 GB file) with an 8K context window, so it fits on a 12 GB GPU.

replit-code-v1_5-3b is a 3.32B-parameter Replit model in GGUF format, quantized by tzhenghao. Its trained context length is 4K tokens. The repository has 1 quant file, from 6.6 GB (BF16) to 6.6 GB (BF16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
BF166.6 GB 7.7 GB
Tight Get file →

What GPU do you need for replit-code-v1_5-3b?

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: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: the best quant that fits is BF16 (6.6 GB file, about 8.2 GB in use).

Which replit-code-v1_5-3b quant should you choose?

BF16 (6.6 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturempt
Parameters3.32B
Layers32
Trained context4,096 tokens
KV cache (fp16)128 KB per token

Source

Quantized bytzhenghao
FamilyReplit
Licenseapache-2.0
Downloads (HF)44
Last updated2024-07-10

Frequently asked questions about replit-code-v1_5-3b

How much VRAM does replit-code-v1_5-3b need?

About 8.2 GB at BF16 with an 8K context window. That is the 6.6 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 replit-code-v1_5-3b on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 8.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of replit-code-v1_5-3b GGUF?

It depends on the quant: BF16 is 6.6 GB.

What context length does replit-code-v1_5-3b support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 1.1 GB at 8K and 0.5 GB at 4K.

Where can I download replit-code-v1_5-3b GGUF?

The files are on Hugging Face in the tzhenghao/replit-code-v1_5-3b-bf16.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 replit-code-v1_5-3b 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.

Similar models

Browse all →

More from tzhenghao

All by tzhenghao →

More Replit models

All Replit →

Other tiny models

All tiny models →