LL

llama2 70B Q4 K M

LlamaGGUF by siacusUpdated 2024-04-10
Download on Hugging Face
Parameters69B
Context4K
Layers80
Architecturellama
Smallest quant41.4 GB
Quick answer

llama2 70B Q4 K M 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.

llama2 70B Q4 K M is a 69B-parameter Llama model in GGUF format, quantized by siacus. Its trained context length is 4K tokens. The repository has 1 quant file, from 41.4 GB (Q4_K_M) to 41.4 GB (Q4_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M41.4 GB 43.3 GB
Too big Get file →

What GPU do you need for llama2 70B Q4 K M?

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 llama2 70B Q4 K M quant should you choose?

Q4_K_M is the usual starting point for llama2 70B Q4 K M: it balances file size and quality well. Here it is a 41.4 GB file.

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 bysiacus
FamilyLlama
Downloads (HF)9
Last updated2024-04-10

Frequently asked questions about llama2 70B Q4 K M

How much VRAM does llama2 70B Q4 K M 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 llama2 70B Q4 K M on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 44.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of llama2 70B Q4 K M GGUF?

It depends on the quant: Q4_K_M is 41.4 GB.

What context length does llama2 70B Q4 K M 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 llama2 70B Q4 K M GGUF?

The files are on Hugging Face in the siacus/llama2-70B-Q4_K_M.gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

More from siacus

All by siacus →

More Llama models

All Llama →

Other large models

All large models →