LL

mattshumer Meta Llama 3 8B Instruct LongTest

LlamaGGUF by RichardErkhovUpdated 2024-10-05
Download on Hugging Face
Parameters8.03B
Context31K
Layers—
Architecturellama
Smallest quant2.0 GB
Quick answer

mattshumer Meta Llama 3 8B Instruct LongTest needs about 4.4 GB of memory at IQ3_XS (a 3.5 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 6 quants, from 2.0 GB (Q3_K) to 3.8 GB (IQ3_M).

mattshumer Meta Llama 3 8B Instruct LongTest is a 8.03B-parameter Llama model in GGUF format, quantized by RichardErkhov. Its trained context length is 31K tokens. The repository has 6 quant files, from 2.0 GB (Q3_K) to 3.8 GB (IQ3_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K2.0 GB 2.7 GB
Fits Get file →
Q2_K3.2 GB 4.1 GB
Fits Get file →
IQ3_XS3.5 GB 4.4 GB
Fits Get file →
Q3_K_S3.7 GB 4.6 GB
Fits Get file →
IQ3_S3.7 GB 4.6 GB
Fits Get file →
IQ3_M3.8 GB 4.7 GB
Fits Get file →

What GPU do you need for mattshumer Meta Llama 3 8B Instruct LongTest?

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 Q3_K (2.0 GB file, about 2.7 GB in use).
  • 6 GB VRAM: the best quant that fits is IQ3_M (3.8 GB file, about 4.7 GB in use).

Which mattshumer Meta Llama 3 8B Instruct LongTest quant should you choose?

IQ3_XS (3.5 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

If memory is tight, the smallest file is Q3_K at 2.0 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters8.03B
Trained context32,000 tokens

Source

Quantized byRichardErkhov
FamilyLlama
Downloads (HF)43
Last updated2024-10-05

Frequently asked questions about mattshumer Meta Llama 3 8B Instruct LongTest

How much VRAM does mattshumer Meta Llama 3 8B Instruct LongTest need?

About 4.4 GB at IQ3_XS with an 8K context window. That is the 3.5 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 mattshumer Meta Llama 3 8B Instruct LongTest on an 8 GB GPU?

Yes, with IQ3_M: the 3.8 GB file needs about 4.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of mattshumer Meta Llama 3 8B Instruct LongTest GGUF?

It depends on the quant: Q3_K is 2.0 GB, Q2_K is 3.2 GB, IQ3_XS is 3.5 GB, Q3_K_S is 3.7 GB, IQ3_S is 3.7 GB, IQ3_M is 3.8 GB.

What context length does mattshumer Meta Llama 3 8B Instruct LongTest support?

The GGUF header lists a trained context length of 32,000 tokens (31K).

Where can I download mattshumer Meta Llama 3 8B Instruct LongTest GGUF?

The files are on Hugging Face in the RichardErkhov/mattshumer_-_Meta-Llama-3-8B-Instruct-LongTest-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 RichardErkhov

All by RichardErkhov →

More Llama models

All Llama →

Other small models

All small models →