RE

RedPajama INCITE Chat 3B gguf chunked

RedpajamaGGUF by BoscoTheDogUpdated 2024-06-15
Download on Hugging Face
Parameters2.78B
Context2K
Layers32
Architecturegptneox
Smallest quant1.6 GB
Quick answer

RedPajama INCITE Chat 3B gguf chunked needs about 4.8 GB of memory at Q4_0 (a 1.6 GB file) with an 8K context window, so it fits on a 6 GB GPU.

RedPajama INCITE Chat 3B gguf chunked is a 2.78B-parameter Redpajama model in GGUF format, quantized by BoscoTheDog. Its trained context length is 2K tokens. The repository has 1 quant file, from 1.6 GB (Q4_0) to 1.6 GB (Q4_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_01.6 GB (12 parts) 2.8 GB
Fits Get file →

What GPU do you need for RedPajama INCITE Chat 3B gguf chunked?

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: the best quant that fits is Q4_0 (1.6 GB file, about 4.8 GB in use).

Which RedPajama INCITE Chat 3B gguf chunked quant should you choose?

Q4_0 (1.6 GB) is the middle option in this repository. 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

Architecturegptneox
Parameters2.78B
Layers32
Trained context2,048 tokens
KV cache (fp16)320 KB per token

Source

Quantized byBoscoTheDog
FamilyRedpajama
Downloads (HF)5
Last updated2024-06-15

Frequently asked questions about RedPajama INCITE Chat 3B gguf chunked

How much VRAM does RedPajama INCITE Chat 3B gguf chunked need?

About 4.8 GB at Q4_0 with an 8K context window. That is the 1.6 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 RedPajama INCITE Chat 3B gguf chunked on an 8 GB GPU?

Yes, with Q4_0: the 1.6 GB file needs about 4.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of RedPajama INCITE Chat 3B gguf chunked GGUF?

It depends on the quant: Q4_0 is 1.6 GB.

What context length does RedPajama INCITE Chat 3B gguf chunked support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 2.7 GB at 8K and 0.7 GB at 2K.

Where can I download RedPajama INCITE Chat 3B gguf chunked GGUF?

The files are on Hugging Face in the BoscoTheDog/RedPajama_INCITE_Chat_3B_gguf_chunked 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 BoscoTheDog

All by BoscoTheDog →

More Redpajama models

All Redpajama →

Other tiny models

All tiny models →