LL

meta-llama-7b

LlamaGGUF by TheBlokeUpdated 2023-09-20
Download on Hugging Face
Parameters6.74B
Context2K
Layers32
Architecturellama
Smallest quant2.8 GB
Quick answer

meta-llama-7b needs about 8.9 GB of memory at Q4_K_M (a 4.1 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 12 quants, from 2.8 GB (Q2_K) to 7.2 GB (Q8_0).

Meta LLaMA 7B in GGUF format

Meta LLaMA 7B is a 6.74 billion parameter language model available in GGUF format. It supports up to 2048 context tokens and is distributed by TheBloke. The model is compatible with llama.cpp and several web UIs.

Good at

  • Chat and support
  • Text generation
  • Storytelling

Limits

  • No vision support
  • License is other
  • No mixture of experts

Best for

  • Local chat applications
  • Web UI demos
  • Python integration

Who it’s for. Developers and researchers who need a lightweight LLaMA 7B model for local inference. The model is suitable for CPU or GPU use via llama.cpp or compatible libraries.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K2.8 GB 4.4 GB
Fits Get file →
Q3_K_S2.9 GB 4.5 GB
Fits Get file →
Q3_K_M3.3 GB 4.9 GB
Fits Get file →
Q3_K_L3.6 GB 5.2 GB
Fits Get file →
Q4_03.8 GB 5.4 GB
Fits Get file →
Q4_K_S3.9 GB 5.4 GB
Fits Get file →
Q4_K_M4.1 GB 5.7 GB
Fits Get file →
Q5_04.7 GB 6.2 GB
Fits Get file →
Q5_K_S4.7 GB 6.2 GB
Fits Get file →
Q5_K_M4.8 GB 6.4 GB
Fits Get file →
Q6_K5.5 GB 7.1 GB
Fits Get file →
Q8_07.2 GB 8.7 GB
Too big Get file →

For 8 GB VRAM use Q4_K_M (est. 8.9 GB). For 12 GB VRAM use Q4_0 (est. 8.6 GB). For 16 GB VRAM use Q5_K_M (est. 9.6 GB).

What GPU do you need for meta-llama-7b?

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: the best quant that fits is Q3_K_S (2.9 GB file, about 7.7 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (7.2 GB file, about 12.0 GB in use).

Which meta-llama-7b quant should you choose?

Q4_K_M is the usual starting point for meta-llama-7b: it balances file size and quality well. Here it is a 4.1 GB file.

The Q8_0 file is 7.2 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 2.8 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
Parameters6.74B
Layers32
Trained context2,048 tokens
KV cache (fp16)512 KB per token

Source

Quantized byTheBloke
FamilyLlama
Licenseother
Downloads (HF)2,831
Last updated2023-09-20

Frequently asked questions about meta-llama-7b

How much VRAM does meta-llama-7b need?

About 8.9 GB at Q4_K_M with an 8K context window. That is the 4.1 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 meta-llama-7b on an 8 GB GPU?

Yes, with Q3_K_S: the 2.9 GB file needs about 7.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of meta-llama-7b GGUF?

It depends on the quant: Q2_K is 2.8 GB, Q3_K_S is 2.9 GB, Q3_K_M is 3.3 GB, Q3_K_L is 3.6 GB, Q4_0 is 3.8 GB, Q4_K_S is 3.9 GB and 6 more.

What context length does meta-llama-7b support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 4.3 GB at 8K and 1.1 GB at 2K.

Where can I download meta-llama-7b GGUF?

The files are on Hugging Face in the TheBloke/LLaMA-7b-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 meta-llama-7b use?

Hugging Face lists the license as other. 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?

Yes, the Q4_K_M quantization requires about 8.9 GB of VRAM at 8k context, which fits in 8 GB with some overhead.

Does this model support vision tasks?

No, the model has no vision capabilities.

Which quantization should I choose for best speed?

Lower bit quantizations like Q2_K or Q3_K_S provide faster inference but use more VRAM.

Similar models

Browse all →

More from TheBloke

All by TheBloke →

More Llama models

All Llama →

Other small models

All small models →