LL

Llama 3 Ko Luxia Instruct

LlamaGGUF by QuantFactoryUpdated 2024-06-28
Download on Hugging Face
Parameters8.17B
Context8K
Layers32
Architecturellama
Smallest quant3.3 GB
Quick answer

Llama 3 Ko Luxia Instruct needs about 6.6 GB of memory at Q4_K_M (a 5.0 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 14 quants, from 3.3 GB (Q2_K) to 8.7 GB (Q8_0).

Llama 3 Ko Luxia Instruct – 8.17B parameter instruction model

Llama 3 Ko Luxia Instruct is an 8.17B parameter instruction‑tuned model based on the Llama architecture. It supports a 8192 token context window and follows the ChatML template for prompt formatting. The model is available in multiple GGUF quantizations.

Good at

  • Instruction following
  • ChatML prompt handling
  • Large context support

Limits

  • No vision or multimodal capabilities
  • License not specified
  • No mixture of experts

Best for

  • Chatbot development
  • Text generation with long context
  • Fine‑tuning on custom instruction data

Who it’s for. Developers and researchers needing a lightweight instruction‑tuned Llama model that fits within limited GPU memory. Suitable for local deployment using llama.cpp.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K3.3 GB 4.8 GB
Fits Get file →
Q3_K_S3.8 GB 5.3 GB
Fits Get file →
Q3_K_M4.1 GB 5.7 GB
Fits Get file →
Q3_K_L4.4 GB 6.0 GB
Fits Get file →
Q4_04.8 GB 6.3 GB
Fits Get file →
Q4_K_S4.8 GB 6.4 GB
Fits Get file →
Q4_K_M5.0 GB 6.6 GB
Fits Get file →
Q4_15.2 GB 6.8 GB
Fits Get file →
Q5_05.7 GB 7.3 GB
Tight Get file →
Q5_K_S5.7 GB 7.3 GB
Tight Get file →
Q5_K_M5.8 GB 7.4 GB
Tight Get file →
Q5_16.2 GB 7.8 GB
Tight Get file →
Q6_K6.7 GB 8.3 GB
Too big Get file →
Q8_08.7 GB 10.3 GB
Too big Get file →

For 8 GB VRAM, use Q4_0 or Q4_K_S (≈6.3 GB memory at 8k context). For 12 GB VRAM, Q5_0 or Q5_K_S (≈7.3 GB). Higher quality quants like Q6_K or Q8_0 require 8.3 GB or 10.3 GB memory respectively.

What GPU do you need for Llama 3 Ko Luxia Instruct?

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_L (4.4 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_1 (6.2 GB file, about 7.8 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (8.7 GB file, about 10.3 GB in use).

Which Llama 3 Ko Luxia Instruct quant should you choose?

Q4_K_M is the usual starting point for Llama 3 Ko Luxia Instruct: it balances file size and quality well. Here it is a 5.0 GB file.

The Q8_0 file is 8.7 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q2_K at 3.3 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters8.17B
Layers32
Trained context8,192 tokens
KV cache (fp16)128 KB per token

Source

Quantized byQuantFactory
FamilyLlama
Downloads (HF)1,136
Last updated2024-06-28

Frequently asked questions about Llama 3 Ko Luxia Instruct

How much VRAM does Llama 3 Ko Luxia Instruct need?

About 6.6 GB at Q4_K_M with an 8K context window. That is the 5.0 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 Ko Luxia Instruct on an 8 GB GPU?

Yes, with Q5_1: the 6.2 GB file needs about 7.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Llama 3 Ko Luxia Instruct GGUF?

It depends on the quant: Q2_K is 3.3 GB, Q3_K_S is 3.8 GB, Q3_K_M is 4.1 GB, Q3_K_L is 4.4 GB, Q4_0 is 4.8 GB, Q4_K_S is 4.8 GB and 8 more.

What context length does Llama 3 Ko Luxia Instruct support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 1.1 GB at 8K and 1.1 GB at 8K.

Where can I download Llama 3 Ko Luxia Instruct GGUF?

The files are on Hugging Face in the QuantFactory/Llama-3-Ko-Luxia-Instruct-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run this model on 8 GB VRAM?

Yes, using Q4_0 or Q4_K_S quantizations which require about 6.3 GB memory at 8k context.

Does this model support vision tasks?

No, it is purely text‑based and does not include vision capabilities.

What prompt format does it use?

It follows the ChatML template for instruction and response formatting.

Other GGUFs of Llama-3-Ko-Luxia-Instruct

Similar models

Browse all →

More from QuantFactory

All by QuantFactory →

More Llama models

All Llama →

Other small models

All small models →