LL

Legion 1.X LLaMa 70B TEST

LlamaGGUF by TareksTestingUpdated 2025-03-18
Download on Hugging Face
Parameters70.6B
Context128K
Layers80
Architecturellama
Smallest quant49.9 GB
Quick answer

Legion 1.X LLaMa 70B TEST needs about 53.1 GB of memory at its main file (a 49.9 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 3 quants, from 49.9 GB to 49.9 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.

Legion 1.X LLaMa 70B TEST is a 70.6B-parameter Llama model in GGUF format, quantized by TareksTesting. Its trained context length is 128K tokens. The repository has 3 quant files, from 49.9 GB to 49.9 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—49.9 GB 53.1 GB
Too big Get file →
—49.9 GB 53.1 GB
Too big Get file →
—49.9 GB 53.1 GB
Too big Get file →

What GPU do you need for Legion 1.X LLaMa 70B TEST?

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: no quant fits at an 8K context.

Which Legion 1.X LLaMa 70B TEST quant should you choose?

If memory is tight, the smallest file is the first one in the table at 49.9 GB, with the quality trade-offs that come with fewer bits.

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 byTareksTesting
FamilyLlama
Licensellama3.3
Downloads (HF)19
Last updated2025-03-18

Frequently asked questions about Legion 1.X LLaMa 70B TEST

How much VRAM does Legion 1.X LLaMa 70B TEST need?

About 53.1 GB at its main file with an 8K context window. That is the 49.9 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 Legion 1.X LLaMa 70B TEST on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 53.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Legion 1.X LLaMa 70B TEST GGUF?

It depends on the quant: file is 49.9 GB, file is 49.9 GB, file is 49.9 GB.

What context length does Legion 1.X LLaMa 70B TEST 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 Legion 1.X LLaMa 70B TEST GGUF?

The files are on Hugging Face in the TareksTesting/Legion-1.X-LLaMa-70B-TEST-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 Legion 1.X LLaMa 70B TEST use?

Hugging Face lists the license as llama3.3. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Similar models

Browse all →

More from TareksTesting

All by TareksTesting →

More Llama models

All Llama →

Other large models

All large models →