LL

Mlx Community Meta Llama 3.1 70B Instruct Bf16 CORRECTED

LlamaGGUF by tensorblockUpdated 2026-01-27
Download on Hugging Face
Parameters70.6B
Context128K
Layers80
Architecturellama
Smallest quant26.4 GB
Quick answer

Mlx Community Meta Llama 3.1 70B Instruct Bf16 CORRECTED needs about 29.6 GB of memory at BF16 (a 26.4 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 2 quants, from 26.4 GB (BF16) to 34.3 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.

Mlx Community Meta Llama 3.1 70B Instruct Bf16 CORRECTED is a 70.6B-parameter Llama model in GGUF format, quantized by tensorblock. Its trained context length is 128K tokens. The repository has 2 quant files, from 26.4 GB (BF16) to 34.3 GB (BF16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
BF1626.4 GB 29.6 GB
Too big Get file →
BF1634.3 GB 37.5 GB
Too big Get file →

What GPU do you need for Mlx Community Meta Llama 3.1 70B Instruct Bf16 CORRECTED?

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: the best quant that fits is BF16 (26.4 GB file, about 29.6 GB in use).
  • 48 GB VRAM: the best quant that fits is BF16 (34.3 GB file, about 37.5 GB in use).

Which Mlx Community Meta Llama 3.1 70B Instruct Bf16 CORRECTED quant should you choose?

BF16 (26.4 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

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

Frequently asked questions about Mlx Community Meta Llama 3.1 70B Instruct Bf16 CORRECTED

How much VRAM does Mlx Community Meta Llama 3.1 70B Instruct Bf16 CORRECTED need?

About 29.6 GB at BF16 with an 8K context window. That is the 26.4 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 Mlx Community Meta Llama 3.1 70B Instruct Bf16 CORRECTED on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 29.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Mlx Community Meta Llama 3.1 70B Instruct Bf16 CORRECTED GGUF?

It depends on the quant: BF16 is 26.4 GB, BF16 is 34.3 GB.

What context length does Mlx Community Meta Llama 3.1 70B Instruct Bf16 CORRECTED 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 Mlx Community Meta Llama 3.1 70B Instruct Bf16 CORRECTED GGUF?

The files are on Hugging Face in the tensorblock/Meta-Llama-3.1-70B-Instruct-bf16-CORRECTED-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 Mlx Community Meta Llama 3.1 70B Instruct Bf16 CORRECTED use?

Hugging Face lists the license as llama3.1. 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 tensorblock

All by tensorblock →

More Llama models

All Llama →

Other large models

All large models →