LL

Models Meta Llama Llama 3.3 70B Instruct

LlamaGGUF by MaziyarPanahiUpdated 2024-12-07
Download on Hugging Face
Parameters70.6B
Context128K
Layers80
Architecturellama
Smallest quant26.4 GB
Quick answer

Models Meta Llama Llama 3.3 70B Instruct 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 11 quants, from 26.4 GB (Q2_K) to 141.1 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.

Meta Llama 3.3 70B Instruct in GGUF format

This is a 70‑billion‑parameter Llama 3.3 Instruct model converted to GGUF by MaziyarPanahi. It supports a 131072‑token context window and is available in multiple quantizations. The model is licensed under llama3.3 and can be run with llama.cpp and compatible libraries.

Good at

  • Large context handling
  • High‑parameter instruction following
  • Wide language coverage

Limits

  • No vision capabilities
  • Requires large VRAM for higher quants
  • License restricts commercial use

Best for

  • Long‑form content generation
  • Complex instruction chains
  • Research prototyping

Who it’s for. Developers and researchers who need a large‑parameter Llama model for local inference. Suitable for users with GPU resources that can accommodate the memory requirements of the chosen quantization.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K26.4 GB 29.6 GB
Too big Get file →
Q3_K_S30.9 GB 34.1 GB
Too big Get file →
Q3_K_M34.3 GB 37.5 GB
Too big Get file →
Q3_K_L37.1 GB 40.3 GB
Too big Get file →
Q4_K_S40.3 GB 43.5 GB
Too big Get file →
Q4_K_M42.5 GB 45.7 GB
Too big Get file →
Q5_K_S48.7 GB 51.8 GB
Too big Get file →
Q5_K_M49.9 GB 53.1 GB
Too big Get file →
Q6_K57.9 GB (6 parts) 61.1 GB
Too big Get file →
Q8_075.0 GB (6 parts) 78.2 GB
Too big Get file →
—141.1 GB (6 parts) 144.3 GB
Too big Get file →

For 8 GB VRAM use Q2_K (26.38 GB file, ~29.6 GB memory). For 16 GB VRAM use Q4_K_M (42.52 GB file, ~45.7 GB memory). For 24 GB VRAM use Q5_K_M (49.95 GB file, ~53.1 GB memory).

What GPU do you need for Models Meta Llama Llama 3.3 70B Instruct?

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 Q2_K (26.4 GB file, about 29.6 GB in use).
  • 48 GB VRAM: the best quant that fits is Q4_K_M (42.5 GB file, about 45.7 GB in use).

Which Models Meta Llama Llama 3.3 70B Instruct quant should you choose?

Q4_K_M is the usual starting point for Models Meta Llama Llama 3.3 70B Instruct: 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.

If memory is tight, the smallest file is Q2_K at 26.4 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
Parameters70.6B
Layers80
Trained context131,072 tokens
KV cache (fp16)320 KB per token

Source

Quantized byMaziyarPanahi
FamilyLlama
Licensellama3.3
Downloads (HF)41,594
Last updated2024-12-07

Frequently asked questions about Models Meta Llama Llama 3.3 70B Instruct

How much VRAM does Models Meta Llama Llama 3.3 70B Instruct 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 Models Meta Llama Llama 3.3 70B Instruct 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 Models Meta Llama Llama 3.3 70B Instruct GGUF?

It depends on the quant: Q2_K is 26.4 GB, Q3_K_S is 30.9 GB, Q3_K_M is 34.3 GB, Q3_K_L is 37.1 GB, Q4_K_S is 40.3 GB, Q4_K_M is 42.5 GB and 5 more.

What context length does Models Meta Llama Llama 3.3 70B Instruct 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 Models Meta Llama Llama 3.3 70B Instruct GGUF?

The files are on Hugging Face in the MaziyarPanahi/Llama-3.3-70B-Instruct-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 Models Meta Llama Llama 3.3 70B Instruct 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.

Can I run this model on 8 GB VRAM?

Use the Q2_K quantization; it requires about 29.6 GB of VRAM at 8 k context, so 8 GB is insufficient. A smaller quant or lower context is needed.

Does this model support vision tasks?

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

Is the model free to use?

It is licensed under llama3.3, which allows non‑commercial use; check the license for commercial restrictions.

Other GGUFs of Llama-3.3-70B-Instruct

Similar models

Browse all →

More from MaziyarPanahi

All by MaziyarPanahi →

More Llama models

All Llama →

Other large models

All large models →