LL

Llama-3-8B-Instruct-262k

LlamaGGUF by MoMonirUpdated 2024-04-28
Download on Hugging Face
Parameters8.03B
Context256K
Layers32
Architecturellama
Smallest quant4.9 GB
Quick answer

Llama-3-8B-Instruct-262k 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 4.9 GB (Q4_K_M) to 6.6 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Llama-3-8B-Instruct-262k is a 8.03B-parameter Llama model in GGUF format, quantized by MoMonir. Its trained context length is 256K tokens. The repository has 3 quant files, from 4.9 GB (Q4_K_M) to 6.6 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M4.9 GB 6.5 GB
Fits Get file →
Q5_K_M5.7 GB 7.3 GB
Tight Get file →
Q6_K6.6 GB 8.2 GB
Too big Get file →

What GPU do you need for Llama-3-8B-Instruct-262k?

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: the best quant that fits is Q5_K_M (5.7 GB file, about 7.3 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (6.6 GB file, about 8.2 GB in use).

Which Llama-3-8B-Instruct-262k quant should you choose?

Q4_K_M is the usual starting point for Llama-3-8B-Instruct-262k: it balances file size and quality well. Here it is a 4.9 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters8.03B
Layers32
Trained context262,144 tokens
KV cache (fp16)128 KB per token

Source

Quantized byMoMonir
FamilyLlama
Licensellama3
Downloads (HF)38
Last updated2024-04-28

Frequently asked questions about Llama-3-8B-Instruct-262k

How much VRAM does Llama-3-8B-Instruct-262k 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-3-8B-Instruct-262k 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-3-8B-Instruct-262k GGUF?

It depends on the quant: Q4_K_M is 4.9 GB, Q5_K_M is 5.7 GB, Q6_K is 6.6 GB.

What context length does Llama-3-8B-Instruct-262k support?

The GGUF header lists a trained context length of 262,144 tokens (256K). 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-3-8B-Instruct-262k GGUF?

The files are on Hugging Face in the MoMonir/Llama-3-8B-Instruct-262k-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 Llama-3-8B-Instruct-262k use?

Hugging Face lists the license as llama3. 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 MoMonir

All by MoMonir →

More Llama models

All Llama →

Other small models

All small models →