LL

Latxa Llama 3.1 70B Instruct v2 FP8

LlamaGGUF by itzuneUpdated 2026-06-23
Download on Hugging Face
Parameters70.6B
Context128K
Layers80
Architecturellama
Smallest quant42.5 GB
Quick answer

Latxa Llama 3.1 70B Instruct v2 FP8 needs about 45.7 GB of memory at Q4_K_M (a 42.5 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 3 quants, from 42.5 GB (Q4_K_M) to 141.1 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.

Latxa Llama 3.1 70B Instruct v2 FP8 is a 70.6B-parameter Llama model in GGUF format, quantized by itzune. Its trained context length is 128K tokens. The repository has 3 quant files, from 42.5 GB (Q4_K_M) to 141.1 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M42.5 GB 45.7 GB
Too big Get file →
Q8_075.0 GB 78.2 GB
Too big Get file →
—141.1 GB 144.3 GB
Too big Get file →

What GPU do you need for Latxa Llama 3.1 70B Instruct v2 FP8?

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: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: no quant fits at an 8K context.
  • 32 GB VRAM: no quant fits at an 8K context.
  • 48 GB VRAM: the best quant that fits is Q4_K_M (42.5 GB file, about 45.7 GB in use).

Which Latxa Llama 3.1 70B Instruct v2 FP8 quant should you choose?

Q4_K_M is the usual starting point for Latxa Llama 3.1 70B Instruct v2 FP8: it balances file size and quality well. Here it is a 42.5 GB file.

The Q8_0 file is 75.0 GB, about 1.8 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.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters70.6B
Layers80
Trained context131,072 tokens
KV cache (fp16)320 KB per token

Source

Quantized byitzune
FamilyLlama
Licenseother
Downloads (HF)43
Last updated2026-06-23

Frequently asked questions about Latxa Llama 3.1 70B Instruct v2 FP8

How much VRAM does Latxa Llama 3.1 70B Instruct v2 FP8 need?

About 45.7 GB at Q4_K_M with an 8K context window. That is the 42.5 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 Latxa Llama 3.1 70B Instruct v2 FP8 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 45.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Latxa Llama 3.1 70B Instruct v2 FP8 GGUF?

It depends on the quant: Q4_K_M is 42.5 GB, Q8_0 is 75.0 GB, file is 141.1 GB.

What context length does Latxa Llama 3.1 70B Instruct v2 FP8 support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 2.7 GB at 8K and 10.7 GB at 32K.

Where can I download Latxa Llama 3.1 70B Instruct v2 FP8 GGUF?

The files are on Hugging Face in the itzune/Latxa-Llama-3.1-70B-Instruct-v2-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 Latxa Llama 3.1 70B Instruct v2 FP8 use?

Hugging Face lists the license as other. 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 Latxa-Llama-3.1-70B-Instruct-v2

Similar models

Browse all →

More from itzune

All by itzune →

More Llama models

All Llama →

Other large models

All large models →