LL

Llama 3.1 8B Instruct Capybara

LlamaGGUF by agentlansUpdated 2024-08-09
Download on Hugging Face
Parameters8.03B
Context128K
Layers32
Architecturellama
Smallest quant4.0 GB
Quick answer

Llama 3.1 8B Instruct Capybara needs about 6.5 GB of memory at Q4_K_M (a 4.9 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 3 quants, from 4.0 GB (Q3_K_M) to 5.7 GB (Q5_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Llama 3.1 8B Instruct Capybara is a 8.03B-parameter Llama model in GGUF format, quantized by agentlans. Its trained context length is 128K tokens. The repository has 3 quant files, from 4.0 GB (Q3_K_M) to 5.7 GB (Q5_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_M4.0 GB 5.6 GB
Fits Get file →
Q4_K_M4.9 GB 6.5 GB
Fits Get file →
Q5_K_M5.7 GB 7.3 GB
Tight Get file →

What GPU do you need for Llama 3.1 8B Instruct Capybara?

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 Q3_K_M (4.0 GB file, about 5.6 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_K_M (5.7 GB file, about 7.3 GB in use).

Which Llama 3.1 8B Instruct Capybara quant should you choose?

Q4_K_M is the usual starting point for Llama 3.1 8B Instruct Capybara: it balances file size and quality well. Here it is a 4.9 GB file.

If memory is tight, the smallest file is Q3_K_M at 4.0 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
Layers32
Trained context131,072 tokens
KV cache (fp16)128 KB per token

Source

Quantized byagentlans
FamilyLlama
Downloads (HF)24
Last updated2024-08-09

Frequently asked questions about Llama 3.1 8B Instruct Capybara

How much VRAM does Llama 3.1 8B Instruct Capybara need?

About 6.5 GB at Q4_K_M with an 8K context window. That is the 4.9 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 Llama 3.1 8B Instruct Capybara on an 8 GB GPU?

Yes, with Q5_K_M: the 5.7 GB file needs about 7.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Llama 3.1 8B Instruct Capybara GGUF?

It depends on the quant: Q3_K_M is 4.0 GB, Q4_K_M is 4.9 GB, Q5_K_M is 5.7 GB.

What context length does Llama 3.1 8B Instruct Capybara support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download Llama 3.1 8B Instruct Capybara GGUF?

The files are on Hugging Face in the agentlans/Llama-3.1-8B-Instruct-Capybara-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 agentlans

All by agentlans →

More Llama models

All Llama →

Other small models

All small models →