LL

Llama 3 8b 64k PoSE

LlamaGGUF by QuantFactoryUpdated 2024-04-29
Download on Hugging Face
Parameters8.03B
Context128K
Layers32
Architecturellama
Smallest quant3.2 GB
Quick answer

Llama 3 8b 64k PoSE 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 14 quants, from 3.2 GB (Q2_K) to 8.5 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Llama 3 8B 64k PoSE – 8.03B parameters, 64k context

Llama 3 8B 64k PoSE extends the base Llama 3 8B model to a 64k token context using PoSE. It is quantized by QuantFactory and available in multiple GGUF formats. The model is trained on RedPajama V1 data with 300M additional tokens.

Good at

  • Long‑form text generation
  • Context‑heavy dialogue
  • Large context reasoning

Limits

  • No vision support
  • No license information provided
  • Requires 8k context for memory estimates

Best for

  • Chatbots needing long context
  • Document summarization with large inputs
  • Code generation with extended prompt

Who it’s for. Developers building applications that need extended context without switching to larger models. Researchers testing PoSE extensions on Llama 3.0.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K3.2 GB 4.8 GB
Fits Get file →
Q3_K_S3.7 GB 5.2 GB
Fits Get file →
Q3_K_M4.0 GB 5.6 GB
Fits Get file →
Q3_K_L4.3 GB 5.9 GB
Fits Get file →
Q4_04.7 GB 6.2 GB
Fits Get file →
Q4_K_S4.7 GB 6.3 GB
Fits Get file →
Q4_K_M4.9 GB 6.5 GB
Fits Get file →
Q4_15.1 GB 6.7 GB
Fits Get file →
Q5_05.6 GB 7.2 GB
Fits Get file →
Q5_K_S5.6 GB 7.2 GB
Fits Get file →
Q5_K_M5.7 GB 7.3 GB
Tight Get file →
Q5_16.1 GB 7.6 GB
Tight Get file →
Q6_K6.6 GB 8.2 GB
Too big Get file →
Q8_08.5 GB 10.1 GB
Too big Get file →

For 8GB VRAM, use Q4_0 (file size 4.66GB, memory 6.2GB at 8k context). For 12GB VRAM, Q5_0 (5.6GB, 7.2GB). For 24GB VRAM, Q6_K (6.6GB, 8.2GB).

What GPU do you need for Llama 3 8b 64k PoSE?

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 (4.3 GB file, about 5.9 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_1 (6.1 GB file, about 7.6 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (8.5 GB file, about 10.1 GB in use).

Which Llama 3 8b 64k PoSE quant should you choose?

Q4_K_M is the usual starting point for Llama 3 8b 64k PoSE: it balances file size and quality well. Here it is a 4.9 GB file.

The Q8_0 file is 8.5 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 3.2 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
Parameters8.03B
Layers32
Trained context131,072 tokens
KV cache (fp16)128 KB per token

Source

Quantized byQuantFactory
FamilyLlama
Downloads (HF)1,023
Last updated2024-04-29

Frequently asked questions about Llama 3 8b 64k PoSE

How much VRAM does Llama 3 8b 64k PoSE 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 64k PoSE on an 8 GB GPU?

Yes, with Q5_1: the 6.1 GB file needs about 7.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Llama 3 8b 64k PoSE GGUF?

It depends on the quant: Q2_K is 3.2 GB, Q3_K_S is 3.7 GB, Q3_K_M is 4.0 GB, Q3_K_L is 4.3 GB, Q4_0 is 4.7 GB, Q4_K_S is 4.7 GB and 8 more.

What context length does Llama 3 8b 64k PoSE 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 8b 64k PoSE GGUF?

The files are on Hugging Face in the QuantFactory/Llama-3-8b-64k-PoSE-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 8GB VRAM?

Yes, using the Q4_0 quantized file which requires approximately 6.2GB of VRAM at 8k context.

Does this model support image input?

No, it only accepts text input.

What context length does this model support?

It supports up to 64k tokens with PoSE, but memory estimates are given for 8k context.

Other GGUFs of Llama-3-8b-64k-PoSE

Similar models

Browse all →

More from QuantFactory

All by QuantFactory →

More Llama models

All Llama →

Other small models

All small models →