LL

Llama 3.3 70B Instruct

LlamaGGUF by lmstudio-communityUpdated 2024-12-06
Download on Hugging Face
Parameters70.6B
Context128K
Layers80
Architecturellama
Smallest quant37.1 GB
Quick answer

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 4 quants, from 37.1 GB (Q3_K_L) to 75.0 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.

Llama 3.3 70B Instruct – large‑scale instruction‑oriented model

Llama 3.3 70B Instruct is a 70‑billion‑parameter model from Meta‑Llama, optimized for instruction following. It supports a 128k‑token context and is available in several GGUF quantizations. The model is multilingual, covering English, German, French, Italian, Portuguese, Hindi, Spanish, and Thai.

Good at

  • Long‑form instruction completion
  • Multilingual text generation
  • Large context handling

Limits

  • Requires high VRAM for full precision
  • No vision or audio capabilities
  • License restricts commercial use

Best for

  • Developers building chatbots with long context
  • Researchers testing instruction‑tuned LLMs
  • Content creators needing multilingual support

Who it’s for. Engineers and researchers who need a powerful instruction‑oriented LLM with extended context. The model is suitable for applications that can accommodate its memory demands and comply with the llama3.3 license.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_L37.1 GB 40.3 GB
Too big Get file →
Q4_K_M42.5 GB 45.7 GB
Too big Get file →
Q6_K57.9 GB (2 parts) 61.1 GB
Too big Get file →
Q8_075.0 GB (2 parts) 78.2 GB
Too big Get file →

For 8‑GB VRAM, use Q3_K_L (37 GB file, ~40 GB VRAM at 8 k context). For 12‑GB VRAM, Q4_K_M (42 GB file, ~46 GB VRAM). For 24‑GB VRAM, Q6_K (57 GB file, ~61 GB VRAM) or Q8_0 (75 GB file, ~78 GB VRAM). Estimates are approximate.

What GPU do you need for 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: 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 Llama 3.3 70B Instruct quant should you choose?

Q4_K_M is the usual starting point for 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 Q3_K_L at 37.1 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

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 bylmstudio-community
FamilyLlama
Licensellama3.3
Downloads (HF)18,139
Last updated2024-12-06

Frequently asked questions about Llama 3.3 70B Instruct

How much VRAM does 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 Llama 3.3 70B Instruct on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 40.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Llama 3.3 70B Instruct GGUF?

It depends on the quant: Q3_K_L is 37.1 GB, Q4_K_M is 42.5 GB, Q6_K is 57.9 GB, Q8_0 is 75.0 GB.

What context length does 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 Llama 3.3 70B Instruct GGUF?

The files are on Hugging Face in the lmstudio-community/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 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 Llama 3.3 70B Instruct on 8 GB VRAM?

Only with the Q3_K_L quantization; it requires about 40 GB VRAM at 8 k context, so 8 GB is insufficient.

Does the model support image inputs?

No, the model has no vision capabilities.

What languages can it generate?

English, German, French, Italian, Portuguese, Hindi, Spanish, and Thai.

Other GGUFs of Llama-3.3-70B-Instruct

Similar models

Browse all →

More from lmstudio-community

All by lmstudio-community →

More Llama models

All Llama →

Other large models

All large models →