LL

models--MaziyarPanahi--Llama-3-8B-Instruct-64k

LlamaGGUF by MaziyarPanahiUpdated 2024-04-25
Download on Hugging Face
Parameters8B
Context63K
Layers32
Architecturellama
Smallest quant3.2 GB
Quick answer

models--MaziyarPanahi--Llama-3-8B-Instruct-64k 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 11 quants, from 3.2 GB (Q2_K) to 16.1 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Llama‑3 8B Instruct with 64k context, quantized for local use

This model extends Llama‑3 8B Instruct to a 64k token context using PoSE. It is available in multiple GGUF quantizations, all supporting a 64k context length. The model was trained on a subset of RedPajama v1 with 300M tokens between 6k‑8k tokens.

Good at

  • Long‑form text generation
  • Instruction following
  • Large context handling

Limits

  • No vision support
  • License not specified
  • Requires GPU for best performance

Best for

  • Chatbots needing long context
  • Research on extended dialogue
  • Content creation with large prompts

Who it’s for. Developers and researchers who need a local LLM with extended context. The model is suitable for applications that require instruction following and long‑form generation without external APIs.

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_K_S4.7 GB 6.3 GB
Fits Get file →
Q4_K_M4.9 GB 6.5 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 →
Q6_K6.6 GB 8.2 GB
Too big Get file →
Q8_08.5 GB 10.1 GB
Too big Get file →
—16.1 GB 17.6 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (≈6.5 GB memory at 8k context). For 12 GB VRAM, Q5_K_M (≈7.3 GB). If more VRAM is available, Q6_K (≈8.2 GB) or Q8_0 (≈10.1 GB) give higher precision. File sizes are listed in the GGUF files.

What GPU do you need for models--MaziyarPanahi--Llama-3-8B-Instruct-64k?

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_K_M (5.7 GB file, about 7.3 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (8.5 GB file, about 10.1 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (8.5 GB file, about 10.1 GB in use).
  • 24 GB VRAM: the best quant that fits is the main file (16.1 GB file, about 17.6 GB in use).

Which models--MaziyarPanahi--Llama-3-8B-Instruct-64k quant should you choose?

Q4_K_M is the usual starting point for models--MaziyarPanahi--Llama-3-8B-Instruct-64k: 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
Parameters8B
Layers32
Trained context64,000 tokens
KV cache (fp16)128 KB per token

Source

Quantized byMaziyarPanahi
FamilyLlama
Downloads (HF)41,737
Last updated2024-04-25

Frequently asked questions about models--MaziyarPanahi--Llama-3-8B-Instruct-64k

How much VRAM does models--MaziyarPanahi--Llama-3-8B-Instruct-64k 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 models--MaziyarPanahi--Llama-3-8B-Instruct-64k 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 models--MaziyarPanahi--Llama-3-8B-Instruct-64k 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_K_S is 4.7 GB, Q4_K_M is 4.9 GB and 5 more.

What context length does models--MaziyarPanahi--Llama-3-8B-Instruct-64k support?

The GGUF header lists a trained context length of 64,000 tokens (63K). 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 models--MaziyarPanahi--Llama-3-8B-Instruct-64k GGUF?

The files are on Hugging Face in the MaziyarPanahi/Llama-3-8B-Instruct-64k-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, the Q4_K_M quantization uses about 6.5 GB of VRAM at 8k context, which fits within 8 GB.

Does this model support image input?

No, the model has no vision capabilities and only handles text.

What context length does the model support?

All GGUF files support a 64k token context length.

Other GGUFs of Llama-3-8B-Instruct-64k

Similar models

Browse all →

More from MaziyarPanahi

All by MaziyarPanahi →

More Llama models

All Llama →

Other small models

All small models →