LL

llama 3 8b pruned mixed precision

LlamaGGUF by ArslanRoboUpdated 2025-12-18
Download on Hugging Face
Parameters6.34B
Context128K
Layers32
Architecturellama
Smallest quant6.5 GB
Quick answer

llama 3 8b pruned mixed precision needs about 8.1 GB of memory at its main file (a 6.5 GB file) with an 8K context window, so it fits on a 12 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

llama 3 8b pruned mixed precision is a 6.34B-parameter Llama model in GGUF format, quantized by ArslanRobo. Its trained context length is 128K tokens. The repository has 1 quant file, from 6.5 GB to 6.5 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—6.5 GB 8.1 GB
Too big Get file →

What GPU do you need for llama 3 8b pruned mixed precision?

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: no quant fits at an 8K context.
  • 12 GB VRAM: the best quant that fits is the main file (6.5 GB file, about 8.1 GB in use).

Specifications

Architecture from the GGUF header

Architecturellama
Parameters6.34B
Layers32
Trained context131,072 tokens
KV cache (fp16)128 KB per token

Source

Quantized byArslanRobo
FamilyLlama
Licensellama3
Downloads (HF)14
Last updated2025-12-18

Frequently asked questions about llama 3 8b pruned mixed precision

How much VRAM does llama 3 8b pruned mixed precision need?

About 8.1 GB at its main file with an 8K context window. That is the 6.5 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 pruned mixed precision on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 8.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of llama 3 8b pruned mixed precision GGUF?

It depends on the quant: file is 6.5 GB.

What context length does llama 3 8b pruned mixed precision 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 pruned mixed precision GGUF?

The files are on Hugging Face in the ArslanRobo/llama-3-8b-pruned-mixed-precision-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 pruned mixed precision 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.

Other GGUFs of Meta-Llama-3-8B

Similar models

Browse all →

More from ArslanRobo

All by ArslanRobo →

More Llama models

All Llama →

Other small models

All small models →