LL

Llama 2 70B

LlamaGGUF by TheBlokeUpdated 2023-09-27
Download on Hugging Face
Parameters69B
Context4K
Layers80
Architecturellama
Smallest quant29.3 GB
Quick answer

Llama 2 70B needs about 44.6 GB of memory at Q4_K_M (a 41.4 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 10 quants, from 29.3 GB (Q2_K) to 48.8 GB (Q5_K_M).

Llama 2 70B in GGUF format for efficient local inference

Llama 2 70B is a 70‑billion‑parameter language model from Meta. The GGUF version is provided by TheBloke and supports a 4096‑token context window. It is available in multiple quantisations for different memory budgets.

Good at

  • Large‑scale text generation
  • Complex reasoning tasks
  • High‑quality language understanding

Limits

  • No vision support
  • Requires large VRAM for full precision
  • License is llama2

Best for

  • Enterprise chatbot deployments
  • Research prototyping
  • Content creation pipelines

Who it’s for. Developers and researchers who need a powerful LLM for local inference and can provide sufficient GPU memory. The model is suitable for teams that prefer open‑source tooling and GGUF compatibility.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K29.3 GB 31.1 GB
Too big Get file →
Q3_K_S29.9 GB 31.8 GB
Too big Get file →
Q3_K_M33.2 GB 35.0 GB
Too big Get file →
Q3_K_L36.1 GB 38.0 GB
Too big Get file →
Q4_038.9 GB 40.7 GB
Too big Get file →
Q4_K_S39.1 GB 40.9 GB
Too big Get file →
Q4_K_M41.4 GB 43.3 GB
Too big Get file →
Q5_047.5 GB 49.3 GB
Too big Get file →
Q5_K_S47.5 GB 49.3 GB
Too big Get file →
Q5_K_M48.8 GB 50.6 GB
Too big Get file →

For 8 GB VRAM, use Q4_0 (≈42 GB memory at 8k context). For 12 GB VRAM, Q4_K_M (≈44.6 GB). For 16 GB VRAM, Q5_0 (≈50.6 GB). Memory estimates are approximate and depend on context length.

What GPU do you need for Llama 2 70B?

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 (41.4 GB file, about 44.6 GB in use).

Which Llama 2 70B quant should you choose?

Q4_K_M is the usual starting point for Llama 2 70B: it balances file size and quality well. Here it is a 41.4 GB file.

If memory is tight, the smallest file is Q2_K at 29.3 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
Parameters69B
Layers80
Trained context4,096 tokens
KV cache (fp16)320 KB per token

Source

Quantized byTheBloke
FamilyLlama
Licensellama2
Downloads (HF)4,127
Last updated2023-09-27

Frequently asked questions about Llama 2 70B

How much VRAM does Llama 2 70B need?

About 44.6 GB at Q4_K_M with an 8K context window. That is the 41.4 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 Llama 2 70B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 32.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Llama 2 70B GGUF?

It depends on the quant: Q2_K is 29.3 GB, Q3_K_S is 29.9 GB, Q3_K_M is 33.2 GB, Q3_K_L is 36.1 GB, Q4_0 is 38.9 GB, Q4_K_S is 39.1 GB and 4 more.

What context length does Llama 2 70B support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 2.7 GB at 8K and 1.3 GB at 4K.

Where can I download Llama 2 70B GGUF?

The files are on Hugging Face in the TheBloke/Llama-2-70B-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 2 70B use?

Hugging Face lists the license as llama2. 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 2 70B on 8 GB VRAM?

Only with the lowest‑precision quantisations such as Q2_K or Q3_K_S, which still require around 32–33 GB memory at 8k context. 8 GB VRAM is insufficient for any quantisation of this model.

Does this model support vision tasks?

No. Llama 2 70B in GGUF format is a text‑only model with no vision capabilities.

What license applies to this model?

The model is released under the llama2 license, as specified by Meta.

Similar models

Browse all →

More from TheBloke

All by TheBloke →

More Llama models

All Llama →

Other large models

All large models →